EMNLP 2025 Accepted Papers

The full list of 3,211 papers accepted at EMNLP 2025 (Conference on Empirical Methods in Natural Language Processing). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

accepted: 3,211

Examining False Positives under Inference Scaling for Mathematical Reasoningaccepted
Examining Multilingual Embedding Models Cross-Lingually Through LLM-Generated Adversarial Examplesaccepted
ExeCoder: Empowering Large Language Models with Executability Representation for Code Translationaccepted
ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialectsaccepted
ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidanceaccepted
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolationaccepted
Expectation Preference Optimization: Reliable Preference Estimation for Improving the Reasoning Capability of Large Language Modelsaccepted
ExpertGenQA: Open-ended QA generation in Specialized Domainsaccepted
Explainability and Interpretability of Multilingual Large Language Models: A Surveyaccepted
Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamicsaccepted
Explainable Text Classification with LLMs: Enhancing Performance through Dialectical Prompting and Explanation-Guided Trainingaccepted
Explaining Differences Between Model Pairs in Natural Language through Sample Learningaccepted
Explaining Length Bias in LLM-Based Preference Evaluationsaccepted
Explaining novel senses using definition generation with open language modelsaccepted
Explicit Learning and the LLM in Machine Translationaccepted
Exploiting Prompt-induced Confidence for Black-Box Attacks on LLMsaccepted
Exploration-Driven Reinforcement Learning for Expert Routing Improvement in Mixture-of-Experts Language Modelsaccepted
Exploring Artificial Image Generation for Stance Detectionaccepted
Exploring Chain-of-Thought Reasoning for Steerable Pluralistic Alignmentaccepted
Exploring Changes in Nation Perception with Nationality-Assigned Personas in LLMsaccepted
Exploring Context Strategies in LLMs for Discourse-Aware Machine Translationaccepted
Exploring Deductive and Inductive Reasoning Capabilities of Large Language Models in Procedural Planningaccepted
Exploring Hyperbolic Hierarchical Structure for Multimodal Rumor Detectionaccepted
Exploring Large Language Models for Detecting Mental Disordersaccepted
Exploring Model Kinship for Merging Large Language Modelsaccepted
Exploring Paraphrasing Strategies for CEFR A1-Level Constraints in LLMsaccepted
Exploring Quality and Diversity in Synthetic Data Generation for Argument Miningaccepted
Exploring Response Uncertainty in MLLMs: An Empirical Evaluation under Misleading Scenariosaccepted
Exploring and Controlling Diversity in LLM-Agent Conversationaccepted
Exploring and Detecting Self-disclosure in Multi-modal posts on Chinese Social Mediaaccepted
Exploring and Evaluating Multimodal Knowledge Reasoning Consistency of Multimodal Large Language Modelsaccepted
Exploring morphology-aware tokenization: A case study on Spanish language modelingaccepted
Exploring the Generalizability of Factual Hallucination Mitigation via Enhancing Precise Knowledge Utilizationaccepted
Exploring the Hidden Capacity of LLMs for One-Step Text Generationaccepted
Exploring the Hidden Reasoning Process of Large Language Models by Misleading Themaccepted
Exploring the Impact of Personality Traits on LLM Bias and Toxicityaccepted
Exploring the Limitations of Mamba in COPY and CoT Reasoningaccepted
Exploring the Vulnerability of the Content Moderation Guardrail in Large Language Models via Intent Manipulationaccepted
Extending Automatic Machine Translation Evaluation to Book-Length Documentsaccepted
Extracting Conceptual Spaces from LLMs Using Prototype Embeddingsaccepted
Extracting Linguistic Information from Large Language Models: Syntactic Relations and Derivational Knowledgeaccepted
Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Modelsaccepted
Extractive Fact Decomposition for Interpretable Natural Language Inference in one Forward Passaccepted
ExtremeAIGC: Benchmarking LMM Vulnerability to AI-Generated Extremist Contentaccepted
F2TEval: Human-Aligned Multi-Dimensional Evaluation for Figure-to-Text Taskaccepted
FACTCHECKMATE: Preemptively Detecting and Mitigating Hallucinations in LMsaccepted
FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compressionaccepted
FANS: Formal Answer Selection for LLM Natural Language Math Reasoning Using Lean4accepted
FB-Bench: A Fine-Grained Multi-Task Benchmark for Evaluating LLMs’ Responsiveness to Human Feedbackaccepted
FC-Attack: Jailbreaking Multimodal Large Language Models via Auto-Generated Flowchartsaccepted
FESTA: Functionally Equivalent Sampling for Trust Assessment of Multimodal LLMsaccepted
FG-PRM: Fine-grained Hallucination Detection and Mitigation in Language Model Mathematical Reasoningaccepted
FIER: Fine-Grained and Efficient KV Cache Retrieval for Long-context LLM Inferenceaccepted
FIRE: Flexible Integration of Data Quality Ratings for Effective Pretrainingaccepted
FISTAPruner: Layer-wise Post-training Pruning for Large Language Modelsaccepted
FLAIRR-TS - Forecasting LLM-Agents with Iterative Refinement and Retrieval for Time Seriesaccepted
FLAMES: Improving LLM Math Reasoning via a Fine-Grained Analysis of the Data Synthesis Pipelineaccepted
FLARE: Faithful Logic-Aided Reasoning and Explorationaccepted
FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inferenceaccepted
FLUID QA: A Multilingual Benchmark for Figurative Language Usage in Dialogue across English, Chinese, and Koreanaccepted
FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answeringaccepted
FNSCC: Fuzzy Neighborhood-Aware Self-Supervised Contrastive Clustering for Short Textaccepted
FOSSIL: Harnessing Feedback on Suboptimal Samples for Data-Efficient Generalisation with Imitation Learning for Embodied Vision-and-Language Tasksaccepted
FSTs vs ICL: Generalisation in LLMs for an under-resourced languageaccepted
FaMTEB: Massive Text Embedding Benchmark in Persian Languageaccepted
FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Dataaccepted
FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMsaccepted
FacLens: Transferable Probe for Foreseeing Non-Factuality in Fact-Seeking Question Answering of Large Language Modelsaccepted
Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generationaccepted
Facilitating Cross-lingual Transfer of Empathy through Language-independent Latent Diffusion: A Case Study in Chineseaccepted
Facilitating Long Context Understanding via Supervised Chain-of-Thought Reasoningaccepted
Fact Verification on Knowledge Graph via Programmatic Graph Reasoningaccepted
FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Modelsaccepted
Facts Fade Fast: Evaluating Memorization of Outdated Medical Knowledge in Large Language Modelsaccepted
Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Textsaccepted
Fair Text-Attributed Graph Representation Learningaccepted
Fair or Framed? Political Bias in News Articles Generated by LLMsaccepted
FairCoT: Enhancing Fairness in Text-to-Image Generation via Chain of Thought Reasoning with Multimodal Large Language Modelsaccepted
FairGen: Controlling Sensitive Attributes for Fair Generations in Diffusion Models via Adaptive Latent Guidanceaccepted
Fairness in Automatic Speech Recognition Isn’t a One-Size-Fits-Allaccepted
FaithUn: Toward Faithful Forgetting in Language Models by Investigating the Interconnectedness of Knowledgeaccepted
FakeSV-VLM: Taming VLM for Detecting Fake Short-Video News via Progressive Mixture-Of-Experts Adapteraccepted
False Friends Are Not Foes: Investigating Vocabulary Overlap in Multilingual Language Modelsaccepted
Familiarity-Aware Evidence Compression for Retrieval-Augmented Generationaccepted
Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMsaccepted
Fast Quiet-STaR: Thinking Without Thought Tokensaccepted
Fast, Not Fancy: Rethinking G2P with Rich Data and Statistical Modelsaccepted
FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Modelsaccepted
Faster In-Context Learning for LLMs via N-Gram Trie Speculative Decodingaccepted
Faster and Better LLMs via Latency-Aware Test-Time Scalingaccepted
Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Modelsaccepted
FedCoT: Federated Chain-of-Thought Distillation for Large Language Modelsaccepted
FedMABench: Benchmarking Mobile GUI Agents on Decentralized Heterogeneous User Dataaccepted
Federated Retrieval-Augmented Generation: A Systematic Mapping Studyaccepted
Feel the Difference? A Comparative Analysis of Emotional Arcs in Real and LLM-Generated CBT Sessionsaccepted
Ferret: Faster and Effective Automated Red Teaming with Reward-Based Scoring Techniqueaccepted
Few-Shot Learning Translation from New Languagesaccepted
Few-Shot Open-Set Classification via Reasoning-Aware Decompositionaccepted
FiRST: Finetuning Router-Selective Transformers for Input-Adaptive Latency Reductionaccepted
FicSim: A Dataset for Multi-Faceted Semantic Similarity in Long-Form Fictionaccepted
FigEx: Aligned Extraction of Scientific Figures and Captionsaccepted
FilBench: Can LLMs Understand and Generate Filipino?accepted
FillerSpeech: Towards Human-Like Text-to-Speech Synthesis with Filler Insertion and Filler Style Controlaccepted
FinGEAR: Financial Mapping-Guided Enhanced Answer Retrievalaccepted
FinGrAct: A Framework for FINe-GRrained Evaluation of ACTionability in Explainable Automatic Fact-Checkingaccepted
FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Makingaccepted
FinLFQA: Evaluating Attributed Text Generation of LLMs in Financial Long-Form Question Answeringaccepted
FinMTEB: Finance Massive Text Embedding Benchmarkaccepted
FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domainaccepted
FinTrust: A Comprehensive Benchmark of Trustworthiness Evaluation in Finance Domainaccepted
Financial Risk Relation Identification through Dual-view Adaptationaccepted
Finding your MUSE: Mining Unexpected Solutions Engineaccepted
Fine-Tuned Thoughts: Leveraging Chain-of-Thought Reasoning for Industrial Asset Health Monitoringaccepted
Fine-Tuning Encoder-Decoder Models with Contrastive Learning for In-Context Distractor Generationaccepted
Fine-tuning LLMs with Cross-Attention-based Weight Decay for Bias Mitigationaccepted
Finetuning LLMs for Human Behavior Prediction in Social Science Experimentsaccepted
Fingerprinting LLMs through Survey Item Factor Correlation: A Case Study on Humor Style Questionnaireaccepted
Firewall Routing: Blocking Leads to Better Hybrid Inference for LLMsaccepted
FlashAdventure: A Benchmark for GUI Agents Solving Full Story Arcs in Diverse Adventure Gamesaccepted
Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMsaccepted
FlexQuant: A Flexible and Efficient Dynamic Precision Switching Framework for LLM Quantizationaccepted
Flexible Thinking for Multimodal Emotional Support Conversation via Reinforcement Learningaccepted
Flexible-length Text Infilling for Discrete Diffusion Modelsaccepted
Flexibly Utilize Memory for Long-Term Conversation via a Fragment-then-Compose Frameworkaccepted
FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Modelsaccepted
FlowMalTrans: Unsupervised Binary Code Translation for Malware Detection Using Flow-Adapter Architectureaccepted
FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasksaccepted
Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agentsaccepted
Following Length Constraints in Instructionsaccepted
Following Occam’s Razor: Dynamic Combination of Structured Knowledge for Multi-Hop Question Answering using LLMsaccepted
Following the Autoregressive Nature of LLM Embeddings via Compression and Alignmentaccepted
FoodSafeSum: Enabling Natural Language Processing Applications for Food Safety Document Summarization and Analysisaccepted
Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluationaccepted
Foot-In-The-Door: A Multi-turn Jailbreak for LLMsaccepted
For a Fistful of Puns: Evaluating a Puns in Multiword Expressions Identification Algorithm Without Dedicated Datasetaccepted
ForestCast: Open-Ended Event Forecasting with Semantic News Forestaccepted
Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacksaccepted
Forget What You Know about LLMs Evaluations - LLMs are Like a Chameleonaccepted
Forget for Get: A Lightweight Two-phase Gradient Method for Knowledge Editing in Large Language Modelsaccepted
Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearningaccepted
Formalizing Style in Personal Narrativesaccepted
FormosanBench: Benchmarking Low-Resource Austronesian Languages in the Era of Large Language Modelsaccepted
FractalLLM: Lossless Self-Speculative Decoding with Layer Embedded Self-Compressionaccepted
Frame First, Then Extract: A Frame-Semantic Reasoning Pipeline for Zero-Shot Relation Triplet Extractionaccepted
FrameEOL: Semantic Frame Induction using Causal Language Modelsaccepted
Frequency & Compositionality in Emergent Communicationaccepted
Friend or Foe? A Computational Investigation of Semantic False Friends across Romance Languagesaccepted
FroM: Frobenius Norm-Based Data-Free Adaptive Model Mergingaccepted
From A and B to A+B: Can Large Language Models Solve Compositional Math Problems?accepted
From Automation to Autonomy: A Survey on Large Language Models in Scientific Discoveryaccepted
From Benchmark to Better Embeddings: Leveraging Synonym Substitution to Enhance Multimodal Models in Ukrainianaccepted
From Capabilities to Performance: Evaluating Key Functional Properties of LLM Architectures in Penetration Testingaccepted
From Characters to Tokens: Dynamic Grouping with Hierarchical BPEaccepted
From Charts to Fair Narratives: Uncovering and Mitigating Geo-Economic Biases in Chart-to-Textaccepted
From Chat Logs to Collective Insights: Aggregative Question Answeringaccepted
From Confidence to Collapse in LLM Factual Robustnessaccepted
From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learningaccepted
From General Reward to Targeted Reward: Improving Open-ended Long-context Generation Modelsaccepted
From Generation to Detection: A Multimodal Multi-Task Dataset for Benchmarking Health Misinformationaccepted
From Generation to Judgment: Opportunities and Challenges of LLM-as-a-judgeaccepted
From Generic Empathy to Personalized Emotional Support: A Self-Evolution Framework for User Preference Alignmentaccepted
From Ground Trust to Truth: Disparities in Offensive Language Judgments on Contemporary Korean Political Discourseaccepted
From Grounding to Manipulation: Case Studies of Foundation Model Integration in Embodied Robotic Systemsaccepted
From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systemsaccepted
From Implicit Exploration to Structured Reasoning: Guideline and Refinement for LLMsaccepted
From Input Perception to Predictive Insight: Modeling Model Blind Spots Before They Become Errorsaccepted
From Insight to Exploit: Leveraging LLM Collaboration for Adaptive Adversarial Text Generationaccepted
From KMMLU-Redux to Pro: A Professional Korean Benchmark Suite for LLM Evaluationaccepted
From Knowledge to Treatment: Large Language Model Assisted Biomedical Concept Representation for Drug Repurposingaccepted
From Language to Cognition: How LLMs Outgrow the Human Language Networkaccepted
From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinementaccepted
From Noise to Clarity: Filtering Real and LLM-Generated Samples for Enhanced Intent Detectionaccepted
From Parameters to Performance: A Data-Driven Study on LLM Structure and Developmentaccepted
From Personas to Talks: Revisiting the Impact of Personas on LLM-Synthesized Emotional Support Conversationsaccepted
From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learningaccepted
From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Modelsaccepted
From Remembering to Metacognition: Do Existing Benchmarks Accurately Evaluate LLMs?accepted
From Schema to State: Zero-Shot Scheme-Only Dialogue State Tracking via Diverse Synthetic Dialogue and Step-by-Step Distillationaccepted
From Scores to Steps: Diagnosing and Improving LLM Performance in Evidence-Based Medical Calculationsaccepted
From Shortcuts to Balance: Attribution Analysis of Speech-Text Feature Utilization in Distinguishing Original from Machine-Translated Textsaccepted
From Surveys to Narratives: Rethinking Cultural Value Adaptation in LLMsaccepted
From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognitionaccepted
From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrievalaccepted
From Tower to Spire: Adding the Speech Modality to a Translation-Specialist LLMaccepted
From Unaligned to Aligned: Scaling Multilingual LLMs with Multi-Way Parallel Corporaaccepted
From Understanding to Generation: An Efficient Shortcut for Evaluating Language Modelsaccepted
From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Testaccepted
From n-gram to Attention: How Model Architectures Learn and Propagate Bias in Language Modelingaccepted
From perception to production: how acoustic invariance facilitates articulatory learning in a self-supervised vocal imitation modelaccepted
FuseChat: Knowledge Fusion of Chat Modelsaccepted
FusionDTI: Fine-grained Binding Discovery with Token-level Fusion for Drug-Target Interactionaccepted
FuzzAug: Data Augmentation by Coverage-guided Fuzzing for Neural Test Generationaccepted
Fuzzy Reasoning Chain (FRC): An Innovative Reasoning Framework from Fuzziness to Clarityaccepted
F²Bench: An Open-ended Fairness Evaluation Benchmark for LLMs with Factuality Considerationsaccepted
G2: Guided Generation for Enhanced Output Diversity in LLMsaccepted
GAMIC: Graph-Aligned Molecular In-context Learning for Molecule Analysis via LLMsaccepted
GAP: a Global Adaptive Pruning Method for Large Language Modelsaccepted
GASE: Generatively Augmented Sentence Encodingaccepted
GATEAU: Selecting Influential Samples for Long Context Alignmentaccepted
GAttention: Gated Attention for the Detection of Abusive Languageaccepted
GCML: Gradient Coherence Guided Meta-Learning for Cross-Domain Emerging Topic Rumor Detectionaccepted
GDLLM: A Global Distance-aware Modeling Approach Based on Large Language Models for Event Temporal Relation Extractionaccepted
GENUINE: Graph Enhanced Multi-level Uncertainty Estimation for Large Language Modelsaccepted
GER-LLM: Efficient and Effective Geospatial Entity Resolution with Large Language Modelaccepted
GLIMPSE: Do Large Vision-Language Models Truly Think With Videos or Just Glimpse at Them?accepted
GLProtein: Global-and-Local Structure Aware Protein Representation Learningaccepted
GRAD: Generative Retrieval-Aligned Demonstration Sampler for Efficient Few-Shot Reasoningaccepted
GRADA: Graph-based Reranking against Adversarial Documents Attackaccepted
GRADE: Generating multi-hop QA and fine-gRAined Difficulty matrix for RAG Evaluationaccepted
GRAID: Synthetic Data Generation with Geometric Constraints and Multi-Agentic Reflection for Harmful Content Detectionaccepted
GRASP: Replace Redundant Layers with Adaptive Singular Parameters for Efficient Model Compressionaccepted
GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Modelsaccepted
GRIT: Guided Relational Integration for Efficient Multi-Table Understandingaccepted
GRPO-Guided Modality Selection Enhanced LoRA-Tuned LLMs for Multimodal Emotion Recognitionaccepted
GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Modelsaccepted
GRV-KBQA: A Three-Stage Framework for Knowledge Base Question Answering with Decoupled Logical Structure, Semantic Grounding and Structure-Aware Validationaccepted
GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Modelsaccepted
GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generationaccepted
GUI-Bee: Align GUI Action Grounding to Novel Environments via Autonomous Explorationaccepted
Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Modelsaccepted
GeLoRA: Geometric Adaptive Ranks For Efficient LoRA Fine-tuningaccepted
GenLink: Generation-Driven Schema-Linking via Multi-Model Learning for Text-to-SQLaccepted
GenPTQ: Green Post-Training Quantization for Large-Scale ASR Models with Mixed-Precision Bit Allocationaccepted
GenPilot: A Multi-Agent System for Test-Time Prompt Optimization in Image Generationaccepted
GenPoE: Generative Passage-level Mixture of Experts for Knowledge Enhancement of LLMsaccepted
Generation-Augmented Retrieval: Rethinking the Role of Large Language Models in Zero-Shot Relation Extractionaccepted
Generative Annotation for ASR Named Entity Correctionaccepted
Generative or Discriminative? Revisiting Text Classification in the Era of Transformersaccepted
Generator-Assistant Stepwise Rollback Framework for Large Language Model Agentaccepted
Genre Matters: How Text Types Interact with Decoding Strategies and Lexical Predictors in Shaping Reading Behavioraccepted
GeoChain: Multimodal Chain-of-Thought for Geographic Reasoningaccepted
GeoDANO: Geometric VLM with Domain Agnostic Vision Encoderaccepted
GeoEdit: Geometric Knowledge Editing for Large Language Modelsaccepted
GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric Reasoningaccepted
Glider: Global and Local Instruction-Driven Expert Routeraccepted
Glitter: A Multi-Sentence, Multi-Reference Benchmark for Gender-Fair German Machine Translationaccepted
GmSLM : Generative Marmoset Spoken Language Modelingaccepted
Golden Touchstone: A Comprehensive Bilingual Benchmark for Evaluating Financial Large Language Modelsaccepted
Good Intentions Beyond ACL: Who Does NLP for Social Good, and Where?accepted
Governance in Motion: Co-evolution of Constitutions and AI models for Scalable Safetyaccepted
GraDaSE: Graph-Based Dataset Search with Examplesaccepted
Graceful Forgetting in Generative Language Modelsaccepted
Graders Should Cheat: Privileged Information Enables Expert-Level Automated Evaluationsaccepted
Gradient-Attention Guided Dual-Masking Synergetic Framework for Robust Text-based Person Retrievalaccepted
Grammar Pruning: Enabling Low-Latency Zero-Shot Task-Oriented Language Models for Edge AIaccepted
Graph-Based Multi-Trait Essay Scoringaccepted
Graph-Guided Textual Explanation Generation Frameworkaccepted
Graph-R1: Incentivizing the Zero-Shot Graph Learning Capability in LLMs via Explicit Reasoningaccepted
Graph-Reward-SQL: Execution-Free Reinforcement Learning for Text-to-SQL via Graph Matching and Stepwise Rewardaccepted
GraphAgent: Agentic Graph Language Assistantaccepted
GraphCheck: Multipath Fact-Checking with Entity-Relationship Graphsaccepted
GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Evictionaccepted
GreekBarBench: A Challenging Benchmark for Free-Text Legal Reasoning and Citationsaccepted
Grounded Semantic Role Labelling from Synthetic Multimodal Data for Situated Robot Commandsaccepted
Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Modelsaccepted
Grounding Multilingual Multimodal LLMs With Cultural Knowledgeaccepted
Group-Aware Reinforcement Learning for Output Diversity in Large Language Modelsaccepted
Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groupsaccepted
Grouping Entities with Shared Properties using Multi-Facet Prompting and Property Embeddingsaccepted
Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guaranteesaccepted
Guess What I am Thinking: A Benchmark for Inner Thought Reasoning of Role-Playing Language Agentsaccepted
GuessingGame: Measuring the Informativeness of Open-Ended Questions in Large Language Modelsaccepted
GuiLoMo: Allocating Experts and Ranks for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectorsaccepted
Guiding Large Language Models for Biomedical Entity Linking via Restrictive and Contrastive Decodingaccepted
HARE: an entity and relation centric evaluation framework for histopathology reportsaccepted
HATECAT-TR: A Hate Speech Span Detection and Categorization Dataset for Turkishaccepted
HAWK: Highlighting Entity-aware Knowledge for Alleviating Information Sparsity in Long Contextsaccepted
HD-PiSSA: High-Rank Distributed Orthogonal Adaptationaccepted
HDiff: Confidence-Guided Denoising Diffusion for Robust Hyper-relational Link Predictionaccepted
HEAL: A Hypothesis-Based Preference-Aware Analysis Frameworkaccepted
HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Modelsaccepted
HEAL: Hybrid Enhancement with LLM-based Agents for Text-attributed Hypergraph Self-supervised Representation Learningaccepted
HELENE: Hessian Layer-wise Clipping and Gradient Annealing for Accelerating Fine-tuning LLM with Zeroth-order Optimizationaccepted
HESEIA: A community-based dataset for evaluating social biases in large language models, co-designed in real school settings in Latin Americaaccepted
HGAdapter: Hypergraph-based Adapters in Language Models for Code Summarization and Clone Detectionaccepted
HICode: Hierarchical Inductive Coding with LLMsaccepted
HIRAG: Hierarchical-Thought Instruction-Tuning Retrieval-Augmented Generationaccepted
HMCL: Task-Optimal Text Representation Adaptation through Hierarchical Contrastive Learningaccepted
HMoE: Heterogeneous Mixture of Experts for Language Modelingaccepted
HS-STaR: Hierarchical Sampling for Self-Taught Reasoners via Difficulty Estimation and Budget Reallocationaccepted
HVGuard: Utilizing Multimodal Large Language Models for Hateful Video Detectionaccepted
HYDRA: A Multi-Head Encoder-only Architecture for Hierarchical Text Classificationaccepted
Hallucination Detection in LLMs Using Spectral Features of Attention Mapsaccepted
Hallucination Detection in Structured Query Generation via LLM Self-Debatingaccepted
Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreationaccepted
HapticCap: A Multimodal Dataset and Task for Understanding User Experience of Vibration Haptic Signalsaccepted
Hard Negatives, Hard Lessons: Revisiting Training Data Quality for Robust Information Retrieval with LLMsaccepted
Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inferenceaccepted
Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encodingaccepted
Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Modelsaccepted
HealthCards: Exploring Text-to-Image Generation as Visual Aids for Healthcare Knowledge Democratizing and Educationaccepted
HebID: Detecting Social Identities in Hebrew-language Political Textaccepted
HetGCoT: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Academic Question Answeringaccepted
HiMATE: A Hierarchical Multi-Agent Framework for Machine Translation Evaluationaccepted
Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agentsaccepted
Hidden in Plain Sight: Reasoning in Underspecified and Misspecified Scenarios for Multimodal LLMsaccepted
HierPrompt: Zero-Shot Hierarchical Text Classification with LLM-Enhanced Prototypesaccepted
Hierarchical Bracketing Encodings Work for Dependency Graphsaccepted
Hierarchical Reward Modeling for Fault Localization in Large Code Repositoriesaccepted
HighMATH: Evaluating Math Reasoning of Large Language Models in Breadth and Depthaccepted
HomoGraphAdapter: A Homogeneous Graph Neural Network as an Effective Adapter for Vision-Language Modelsaccepted
HookMoE: A learnable performance compensation strategy of Mixture-of-Experts for LLM inference accelerationaccepted
Hope vs. Hate: Understanding User Interactions with LGBTQ+ News Content in Mainstream US News Media through the Lens of Hope Speechaccepted
Hopscotch: Discovering and Skipping Redundancies in Language Modelsaccepted
How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on tau-benchaccepted
How Diversely Can Language Models Solve Problems? Exploring the Algorithmic Diversity of Model-Generated Codeaccepted
How Do Large Language Models Perform on PDE Discovery: A Coarse-to-fine Perspectiveaccepted
How Do Large Vision-Language Models See Text in Image? Unveiling the Distinctive Role of OCR Headsaccepted
How Do Social Bots Participate in Misinformation Spread? A Comprehensive Dataset and Analysisaccepted
How Does Cognitive Bias Affect Large Language Models? A Case Study on the Anchoring Effect in Price Negotiation Simulationsaccepted
How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysisaccepted
How Does Knowledge Selection Help Retrieval Augmented Generation?accepted
How Far Can LLMs Improve from Experience? Measuring Test-Time Learning Ability in LLMs with Human Comparisonaccepted
How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Modelsaccepted
How Is LLM Reasoning Distracted by Irrelevant Context? An Analysis Using a Controlled Benchmarkaccepted
How Jailbreak Defenses Work and Ensemble? A Mechanistic Investigationaccepted
How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucinationaccepted
How Much Do Large Language Models Know about Human Motion? A Case Study in 3D Avatar Controlaccepted
How Persuasive Is Your Context?accepted
How Private are Language Models in Abstractive Summarization?accepted
How Real Are Synthetic Therapy Conversations? Evaluating Fidelity in Prolonged Exposure Dialoguesaccepted
How Reliable is Multilingual LLM-as-a-Judge?accepted
How Sampling Affects the Detectability of Machine-written texts: A Comprehensive Studyaccepted
How Sememic Components Can Benefit Link Prediction for Lexico-Semantic Knowledge Graphs?accepted
How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts?accepted
How a Bilingual LM Becomes Bilingual: Tracing Internal Representations with Sparse Autoencodersaccepted
How do Language Models Generate Slang: A Systematic Comparison between Human and Machine-Generated Slang Usagesaccepted
How do Language Models Reshape Entity Alignment? A Survey of LM-Driven EA Methods: Advances, Benchmarks, and Futureaccepted
How do autoregressive transformers solve full addition?accepted
How to Generalize the Detection of AI-Generated Text: Confounding Neuronsaccepted
How to Make Large Language Models Generate 100% Valid Molecules?accepted
How to Protect Yourself from 5G Radiation? Investigating LLM Responses to Implicit Misinformationaccepted
How to inject knowledge efficiently? Knowledge Infusion Scaling Law for Pre-training Large Language Modelsaccepted
Human-Inspired Obfuscation for Model Unlearning: Local and Global Strategies with Hyperbolic Representationsaccepted
Humanity’s Last Code Exam: Can Advanced LLMs Conquer Human’s Hardest Code Competition?accepted
Humanizing Machines: Rethinking LLM Anthropomorphism Through a Multi-Level Framework of Designaccepted
Humans Hallucinate Too: Language Models Identify and Correct Subjective Annotation Errors With Label-in-a-Haystack Promptsaccepted
Humor in Pixels: Benchmarking Large Multimodal Models Understanding of Online Comicsaccepted
HydraOpt: Navigating the Efficiency-Performance Trade-off of Adapter Mergingaccepted
HydraRAG: Structured Cross-Source Enhanced Large Language Model Reasoningaccepted
HypER: Literature-grounded Hypothesis Generation and Distillation with Provenanceaccepted
HyperKGR: Knowledge Graph Reasoning in Hyperbolic Space with Graph Neural Network Encoding Symbolic Pathaccepted
I-GUARD: Interpretability-Guided Parameter Optimization for Adversarial Defenseaccepted
ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignmentaccepted
ICL CIPHERS: Quantifying ”Learning” in In-Context Learning via Substitution Ciphersaccepted
ICL-Bandit: Relevance Labeling in Advertisement Recommendation Systems via LLMaccepted
ICLER: Intent CLassification with Enhanced Reasoningaccepted
ICR: Iterative Clarification and Rewriting for Conversational Searchaccepted
IG-Pruning: Input-Guided Block Pruning for Large Language Modelsaccepted
IIET: Efficient Numerical Transformer via Implicit Iterative Euler Methodaccepted
IL-PCSR: Legal Corpus for Prior Case and Statute Retrievalaccepted
INDOORWORLD : Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environmentaccepted
INREACT: An Inspire-Then-Reinforce Training Framework For Multimodal GUI Agentaccepted
IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Dataaccepted
IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agentsaccepted
ISACL: Internal State Analyzer for Copyrighted Training Data Leakageaccepted
Icon2: Aligning Large Language Models Using Self-Synthetic Preference Data via Inherent Regulationaccepted
Identification of Multiple Logical Interpretations in Counter-Argumentsaccepted
Identifying & Interactively Refining Ambiguous User Goals for Data Visualization Code Generationaccepted
Identifying Aspects in Peer Reviewsaccepted
Identifying Noise in Human-Created Datasets using Training Dynamics from Generative Modelsaccepted
Identifying Pre-training Data in LLMs: A Neuron Activation-Based Detection Frameworkaccepted
Identifying Rare Languages in Common Crawl Data is a Needles-in-a-Haystack Problemaccepted
Identifying Unlearned Data in LLMs via Membership Inference Attacksaccepted
Identifying and Answering Questions with False Assumptions: An Interpretable Approachaccepted
Idiosyncratic Versus Normative Modeling of Atypical Speech Recognition: Dysarthric Case Studiesaccepted
Idola Tribus of AI: Large Language Models tend to perceive order where none existsaccepted
Igniting Creative Writing in Small Language Models: LLM-as-a-Judge versus Multi-Agent Refined Rewardsaccepted
Image Difference Captioning via Adversarial Preference Optimizationaccepted
Image Embedding Sampling Method for Diverse Captioningaccepted
Imagination and Contemplation: A Balanced Framework for Semantic-Augmented Multimodal Machine Translationaccepted
ImpRAG: Retrieval-Augmented Generation with Implicit Queriesaccepted
ImpliRet: Benchmarking the Implicit Fact Retrieval Challengeaccepted
Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulationsaccepted
Implicit Values Embedded in How Humans and LLMs Complete Subjective Everyday Tasksaccepted
Improbable Bigrams Expose Vulnerabilities of Incomplete Tokens in Byte-Level Tokenizersaccepted
Improve LLM-as-a-Judge Ability as a General Abilityaccepted
Improving Alignment in LVLMs with Debiased Self-Judgmentaccepted
Improving Chemical Understanding of LLMs via SMILES Parsingaccepted
Improving Clustering with Positive Pairs Generated from LLM-Driven Labelsaccepted
Improving Context Fidelity via Native Retrieval-Augmented Reasoningaccepted
Improving Cross Lingual Transfer by Pretraining with Active Forgettingaccepted
Improving Handshape Representations for Sign Language Processing: A Graph Neural Network Approachaccepted
Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilitiesaccepted
Improving Informally Romanized Language Identificationaccepted
Improving Instruct Models for Free: A Study on Partial Adaptationaccepted
Improving LLM Reasoning through Interpretable Role-Playing Steeringaccepted
Improving LLM-as-a-Judge Inference with the Judgment Distributionaccepted
Improving Language Model Personas via Rationalization with Psychological Scaffoldsaccepted
Improving Large Language Model Safety with Contrastive Representation Learningaccepted
Improving Large Language Models Function Calling and Interpretability via Guided-Structured Templatesaccepted
Improving Low-Resource Sequence Labeling with Knowledge Fusion and Contextual Label Explanationsaccepted
Improving Multilingual Retrieval-Augmented Language Models through Dialectic Reasoning Argumentationsaccepted
Improving Neutral Point-of-View Generation with Data- and Parameter-Efficient RLaccepted
Improving Online Job Advertisement Analysis via Compositional Entity Extractionaccepted
Improving Preference Alignment of LLM with Inference-Free Self-Refinementaccepted
Improving Prompt Generalization for Cross-prompt Essay Trait Scoring from the Scoring-invariance Perspectiveaccepted
Improving Reasoning Capabilities in Small Models through Mixture-of-layers Distillation with Stepwise Attention on Key Informationaccepted
Improving Rule-based Reasoning in LLMs using Neurosymbolic Representationsaccepted
Improving Task Diversity in Label Efficient Supervised Finetuning of LLMsaccepted
Improving Zero-shot Sentence Decontextualisation with Content Selection and Planningaccepted
Improving the Language Understanding Capabilities of Large Language Models Using Reinforcement Learningaccepted
Improving the Quality of Web-mined Parallel Corpora of Low-Resource Languages using Debiasing Heuristicsaccepted
In Benchmarks We Trust ... Or Not?accepted
In-Context Learning Boosts Speech Recognition via Human-like Adaptation to Speakers and Language Varietiesaccepted
InFact: Informativeness Alignment for Improved LLM Factualityaccepted
InMind: Evaluating LLMs in Capturing and Applying Individual Human Reasoning Stylesaccepted
Inceptive Transformers: Enhancing Contextual Representations through Multi-Scale Feature Learning Across Domains and Languagesaccepted
Inclusive Leadership in the Age of AI: A Dataset and Comparative Study of LLMs vs. Real-Life Leaders in Workplace Action Planningaccepted
Incorporating Diverse Perspectives in Cultural Alignment: Survey of Evaluation Benchmarks Through A Three-Dimensional Frameworkaccepted
IndiGEC: Multilingual Grammar Error Correction for Low-Resource Indian Languagesaccepted
IndoSafety: Culturally Grounded Safety for LLMs in Indonesian Languagesaccepted
Inducing Argument Facets for Faithful Opinion Summarizationaccepted
Inductive Reasoning on Few-Shot Knowledge Graphs with Task-Aware Language Modelsaccepted
Inefficiencies of Meta Agents for Agent Designaccepted
InfAL: Inference Time Adversarial Learning for Improving Research Ideationaccepted
InfiMM-WebMath-40B: Advancing Multimodal Pre-Training for Enhanced Mathematical Reasoningaccepted
Infini-gram mini: Exact n-gram Search at the Internet Scale with FM-Indexaccepted
InfiniBench: A Benchmark for Large Multi-Modal Models in Long-Form Movies and TV Showsaccepted
InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filteringaccepted
Information Integration in Large Language Models is Gated by Linguistic Structural Markersaccepted
Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Surveyaccepted
InsBank: Evolving Instruction Subset for Ongoing Alignmentaccepted
Insights into using temporal coordinated behaviour to explore connections between social media posts and influenceaccepted
Instability in Downstream Task Performance During LLM Pretrainingaccepted
Instance-level Randomization: Toward More Stable LLM Evaluationsaccepted
Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basqueaccepted
InteGround: On the Evaluation of Verification and Retrieval Planning in Integrative Groundingaccepted
Integral Transformer: Denoising Attention, Not Too Much Not Too Littleaccepted
Intelligent Document Parsing: Towards End-to-end Document Parsing via Decoupled Content Parsing and Layout Groundingaccepted
Intent-aware Schema Generation and Refinement for Literature Review Tablesaccepted
IntentionFrame: A Semi-Structured, Multi-Aspect Framework for Fine-Grained Conversational Intention Understandingaccepted
Inter-sentence Context Modeling and Structure-aware Representation Enhancement for Conversational Sentiment Quadruple Extractionaccepted
InterFeedback: Unveiling Interactive Intelligence of Large Multimodal Models with Human Feedbackaccepted
InterIDEAS: Philosophical Intertextuality via LLMsaccepted
InteractSpeech: A Speech Dialogue Interaction Corpus for Spoken Dialogue Modelaccepted
Interdisciplinary Research in Conversation: A Case Study in Computational Morphology for Language Documentationaccepted
Interesting Culture: Social Relation Recognition from Videos via Culture De-confoundingaccepted
Internal Chain-of-Thought: Empirical Evidence for Layer‐wise Subtask Scheduling in LLMsaccepted
Internal states before wait modulate reasoning patternsaccepted
Interpretability Analysis of Arithmetic In-Context Learning in Large Language Modelsaccepted
Interpretable Mnemonic Generation for Kanji Learning via Expectation-Maximizationaccepted
Interpretable Text Embeddings and Text Similarity Explanation: A Surveyaccepted
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safetyaccepted
IntrEx: A Dataset for Modeling Engagement in Educational Conversationsaccepted
Intrinsic Test of Unlearning Using Parametric Knowledge Tracesaccepted
Introducing Spotlight: A Novel Approach for Generating Captivating Key Information from Documentsaccepted
Investigating Controversy Framing across Topics on Social Mediaaccepted
Investigating Dictionary Expansion for Video-based Sign Language Dictionariesaccepted
Investigating How Pre-training Data Leakage Affects Models’ Reproduction and Detection Capabilitiesaccepted
Investigating Multi-layer Representations for Dense Passage Retrievalaccepted
Investigating Neurons and Heads in Transformer-based LLMs for Typographical Errorsaccepted
Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval-Augmented Generation Across Learning Stylesaccepted
Investigating Value-Reasoning Reliability in Small Large Language Modelsaccepted
Investigating the Impact of Conceptual Metaphors on LLM-based NLI through Shapley Interactionsaccepted
Investigating the interaction of linguistic and mathematical reasoning in language models using multilingual number puzzlesaccepted
Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarkingaccepted
Invisible Prompts, Visible Threats: Malicious Font Injection in External Resources for Large Language Modelsaccepted
Invoke Interfaces Only When Needed: Adaptive Invocation for Large Language Models in Question Answeringaccepted
IoTMigrator: LLM-driven Embedded IoT Code Migration across Different OSes for Cloud-device Integrationaccepted
Is Cognition Consistent with Perception? Assessing and Mitigating Multimodal Knowledge Conflicts in Document Understandingaccepted
Is Safety Standard Same for Everyone? User-Specific Safety Evaluation of Large Language Modelsaccepted
Is the Top Still Spinning? Evaluating Subjectivity in Narrative Understandingaccepted
Iterative Multilingual Spectral Attribute Erasureaccepted
Iterative Prompt Refinement for Safer Text-to-Image Generationaccepted
It’s All About In-Context Learning! Teaching Extremely Low-Resource Languages to LLMsaccepted
JI2S: Joint Influence‐Aware Instruction Data Selection for Efficient Fine‐Tuningaccepted
JOLT-SQL: Joint Loss Tuning of Text-to-SQL with Confusion-aware Noisy Schema Samplingaccepted
JUDGEBERT: Assessing Legal Meaning Preservation Between Sentencesaccepted
JUREX-4E: Juridical Expert-Annotated Four-Element Knowledge Base for Legal Reasoningaccepted
Jailbreak Attack Initializations as Extractors of Compliance Directionsaccepted
Jailbreak Distillation: Renewable Safety Benchmarkingaccepted
Jailbreak LLMs through Internal Stance Manipulationaccepted
Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibilityaccepted
Jigsaw-Puzzles: From Seeing to Understanding to Reasoning in Vision-Language Modelsaccepted
Job Unfair: An Investigation of Gender and Occupational Bias in Free-Form Text Completions by LLMsaccepted
Joint Enhancement of Relational Reasoning for Long-Context LLMsaccepted
Joint Modeling of Entities and Discourse Relations for Coherence Assessmentaccepted
Journalism-Guided Agentic In-context Learning for News Stance Detectionaccepted
Judge and Improve: Towards a Better Reasoning of Knowledge Graphs with Large Language Modelsaccepted
Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Modelsaccepted
Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplification and Resistance in Multi-Agent Based LLM-as-Judgeaccepted
KAHAN: Knowledge-Augmented Hierarchical Analysis and Narration for Financial Data Narrationaccepted
KBAlign: Efficient Self Adaptation on Specific Textual Knowledge Basesaccepted
KBM: Delineating Knowledge Boundary for Adaptive Retrieval in Large Language Modelsaccepted
KCS: Diversify Multi-hop Question Generation with Knowledge Composition Samplingaccepted
KELE: A Multi-Agent Framework for Structured Socratic Teaching with Large Language Modelsaccepted
KELE: Residual Knowledge Erasure for Enhanced Multi-hop Reasoning in Knowledge Editingaccepted
KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answeringaccepted
KG-CQR: Leveraging Structured Relation Representations in Knowledge Graphs for Contextual Query Retrievalaccepted
KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented Generationaccepted
KGE Calibrator: An Efficient Probability Calibration Method of Knowledge Graph Embedding Models for Trustworthy Link Predictionaccepted
KLAAD: Refining Attention Mechanisms to Reduce Societal Bias in Generative Language Modelsaccepted
KRETA: A Benchmark for Korean Reading and Reasoning in Text-Rich VQA Attuned to Diverse Visual Contextsaccepted
KaeDe: Progressive Generation of Logical Forms via Knowledge-Aware Question Decomposition for Improved KBQAaccepted
Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answeringaccepted
Knowing More, Acting Better: Hierarchical Representation for Embodied Decision-Makingaccepted
Knowledge Editing through Chain-of-Thoughtaccepted
Knowledge Graph-Driven Memory Editing with Directional Interventionsaccepted
Knowledge-Aware Co-Reasoning for Multidisciplinary Collaborationaccepted
Knowledge-enhanced Multimodal ECG Representation Learning with Arbitrary-Lead Inputsaccepted
Ko-LongRAG: A Korean Long-Context RAG Benchmark Built with a Retrieval-Free Approachaccepted
KoACD: The First Korean Adolescent Dataset for Cognitive Distortion Analysis via Role-Switching Multi-LLM Negotiationaccepted
KoBLEX: Open Legal Question Answering with Multi-hop Reasoningaccepted
KoLEG: On-the-Fly Korean Legal Knowledge Editing with Continuous Retrievalaccepted
Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidanceaccepted
Krikri: Advancing Open Large Language Models for Greekaccepted
KurTail : Kurtosis-based LLM Quantizationaccepted
LAGCL4Rec: When LLMs Activate Interactions Potential in Graph Contrastive Learning for Recommendationaccepted
LASER: An LLM-based ASR Scoring and Evaluation Rubricaccepted
LATTE: Learning to Think with Vision Specialistsaccepted
LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocationaccepted
LAWCAT: Efficient Distillation from Quadratic to Linear Attention with Convolution across Tokens for Long Context Modelingaccepted
LC-Eval: A Bilingual Multi-Task Evaluation Benchmark for Long-Context Understandingaccepted
LCAN: A Label-Aware Contrastive Attention Network for Multi-Intent Recognition and Slot Filling in Task-Oriented Dialogue Systemsaccepted
LCES: Zero-shot Automated Essay Scoring via Pairwise Comparisons Using Large Language Modelsaccepted
LEAF: Large Language Diffusion Model for Time Series Forecastingaccepted
LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Expertsaccepted
LGA: LLM-GNN Aggregation for Temporal Evolution Attribute Graph Predictionaccepted
LIDDIA: Language-based Intelligent Drug Discovery Agentaccepted
LIFTED: Multimodal Clinical Trial Outcome Prediction via Large Language Models and Mixture-of-Expertsaccepted
LILaC: Late Interacting in Layered Component Graph for Open-domain Multimodal Multihop Retrievalaccepted
LLM Agents at the Roundtable: A Multi-Perspective and Dialectical Reasoning Framework for Essay Scoringaccepted
LLM Agents for Education: Advances and Applicationsaccepted
LLM Bias Detection and Mitigation through the Lens of Desired Distributionsaccepted
LLM Distillation for Efficient Few-Shot Multiple Choice Question Answeringaccepted
LLM Jailbreak Detection for (Almost) Free!accepted
LLM-Based Web Data Collection for Research Dataset Creationaccepted
LLM-Driven Completeness and Consistency Evaluation for Cultural Heritage Data Augmentation in Cross-Modal Retrievalaccepted
LLM-Driven Implicit Target Augmentation and Fine-Grained Contextual Modeling for Zero-Shot and Few-Shot Stance Detectionaccepted
LLM-Guided Co-Training for Text Classificationaccepted
LLM-Guided Semantic Relational Reasoning for Multimodal Intent Recognitionaccepted
LLM-Independent Adaptive RAG: Let the Question Speak for Itselfaccepted
LLM-OREF: An Open Relation Extraction Framework Based on Large Language Modelsaccepted
LLM-based Conversational Recommendation Agents with Collaborative Verbalized Experienceaccepted
LLM-based Open Domain Planning by Leveraging Entity-Attribute-Level Domain Modelsaccepted
LLM-empowered Dynamic Prompt Routing for Vision-Language Models Tuning under Long-Tailed Distributionsaccepted
LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferencesaccepted
LLMEval-Med: A Real-world Clinical Benchmark for Medical LLMs with Physician Validationaccepted
LLMs Behind the Scenes: Enabling Narrative Scene Illustrationaccepted
LLMs Can Compensate for Deficiencies in Visual Representationsaccepted
LLMs Don’t Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanationsaccepted
LLMs Reproduce Stereotypes of Sexual and Gender Minoritiesaccepted
LLMs are Better Than You Think: Label-Guided In-Context Learning for Named Entity Recognitionaccepted
LLMs are Privacy Erasableaccepted
LLMs as World Models: Data-Driven and Human-Centered Pre-Event Simulation for Disaster Impact Assessmentaccepted
LLMs as a synthesis between symbolic and distributed approaches to languageaccepted
LLMs cannot spot math errors, even when allowed to peek into the solutionaccepted
LLMs for Bayesian Optimization in Scientific Domains: Are We There Yet?accepted
LLMsPark: A Benchmark for Evaluating Large Language Models in Strategic Gaming Contextsaccepted
LLaMP: Large Language Model Made Powerful for High-fidelity Materials Knowledge Retrievalaccepted
LLaVE: Large Language and Vision Embedding Models with Hardness-Weighted Contrastive Learningaccepted
LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encodingaccepted
LM2Protein: A Structure-to-Token Protein Large Language Modelaccepted
LMR-BENCH: Evaluating LLM Agent’s Ability on Reproducing Language Modeling Researchaccepted
LMUNIT: Fine-grained Evaluation with Natural Language Unit Testsaccepted
LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Modelsaccepted
LOHRec: Leveraging Order and Hierarchy in Generative Sequential Recommendationaccepted
LORAXBENCH: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languagesaccepted
LORE: Continual Logit Rewriting Fosters Faithful Generationaccepted
LRPLAN: A Multi-Agent Collaboration of Large Language and Reasoning Models for Planning with Implicit & Explicit Constraintsaccepted
LSRL: Process-Supervised GRPO on Latent Recurrent States Improves Mathematical Reasoningaccepted
LUME: LLM Unlearning with Multitask Evaluationsaccepted
LVLMs are Bad at Overhearing Human Referential Communicationaccepted
LaMDAgent: An Autonomous Framework for Post-Training Pipeline Optimization via LLM Agentsaccepted
LaMP-Cap: Personalized Figure Caption Generation With Multimodal Figure Profilesaccepted
LaMP-QA: A Benchmark for Personalized Long-form Question Answeringaccepted
LaMP-Val: Large Language Models Empower Personalized Valuation in Auctionaccepted
Label Set Optimization via Activation Distribution Kurtosis for Zero-Shot Classification with Generative Modelsaccepted
LangProBe: a Language Program Benchmarkaccepted
Language Mixing in Reasoning Language Models: Patterns, Impact, and Internal Causesaccepted
Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual Transformersaccepted
Language Models Can Easily Learn to Reason from Demonstrationsaccepted
Language Models Can be Efficiently Steered via Minimal Embedding Layer Transformationsaccepted
Language Models Identify Ambiguities and Exploit Loopholesaccepted
Language Models as Causal Effect Generatorsaccepted
Language Models as Continuous Self-Evolving Data Engineersaccepted
Language models can learn implicit multi-hop reasoning, but only if they have lots of training dataaccepted
Language-Guided Temporal Token Pruning for Efficient VideoLLM Processingaccepted
Language-Informed Synthesis of Rational Agent Models for Grounded Theory-of-Mind Reasoning On-the-flyaccepted
Language-Specific Layer Matters: Efficient Multilingual Enhancement for Large Vision-Language Modelsaccepted
Language-to-Space Programming for Training-Free 3D Visual Groundingaccepted
Languages Still Left Behind: Toward a Better Multilingual Machine Translation Benchmarkaccepted
Large Language Model Agents in Finance: A Survey Bridging Research, Practice, and Real-World Deploymentaccepted
Large Language Model Evaluation via Matrix Nuclear-Normaccepted
Large Language Models Badly Generalize across Option Length, Problem Types, and Irrelevant Noun Replacementsaccepted
Large Language Models Discriminate Against Speakers of German Dialectsaccepted
Large Language Models Do Multi-Label Classification Differentlyaccepted
Large Language Models Have Intrinsic Meta-Cognition, but Need a Good Lensaccepted
Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunitiesaccepted
Large Language Models Might Not Care What You Are Saying: Prompt Format Beats Descriptionsaccepted
Large Language Models Threaten Language’s Epistemic and Communicative Foundationsaccepted
Large Language Models as Reader for Bias Detectionaccepted
Large Language Models as Realistic Microservice Trace Generatorsaccepted
Large Language Models for Automated Literature Review: An Evaluation of Reference Generation, Abstract Writing, and Review Compositionaccepted
Large Language Models for Controllable Multi-property Multi-objective Molecule Optimizationaccepted
Large Language Models for Multilingual Previously Fact-Checked Claim Detectionaccepted
Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Predictionaccepted
Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainabilityaccepted
LastingBench: Defend Benchmarks Against Knowledge Leakageaccepted
Latent Inter-User Difference Modeling for LLM Personalizationaccepted
Layer Duplication in LLMsaccepted
Layer-Aware Representation Filtering: Purifying Finetuning Data to Preserve LLM Safety Alignmentaccepted
Layer-Aware Task Arithmetic: Disentangling Task-Specific and Instruction-Following Knowledgeaccepted
Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representationsaccepted
Layered Insights: Generalizable Analysis of Human Authorial Style by Leveraging All Transformer Layersaccepted
LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridizationaccepted
Leaky Thoughts: Large Reasoning Models Are Not Private Thinkersaccepted
LeanK: Learnable K Cache Channel Pruning for Efficient Decodingaccepted
Learn and Unlearn: Addressing Misinformation in Multilingual LLMsaccepted
Learning API Functionality from In-Context Demonstrations for Tool-based Agentsaccepted
Learning Contextual Retrieval for Robust Conversational Searchaccepted
Learning Is Not A Race: Improving Retrieval in Language Models via Equal Learningaccepted
Learning Like Humans: Advancing LLM Reasoning Capabilities via Adaptive Difficulty Curriculum Learning and Expert-Guided Self-Reformulationaccepted
Learning SQL Like a Human: Structure-Aware Curriculum Learning for Text-to-SQL Generationaccepted
Learning Subjective Label Distributions via Sociocultural Descriptorsaccepted
Learning Trajectories of Figurative Language for Pre-Trained Language Modelsaccepted
Learning What to Remember: Adaptive Probabilistic Memory Retention for Memory-Efficient Language Modelsaccepted
Learning from Diverse Reasoning Paths with Routing and Collaborationaccepted
Learning from Few Samples: A Novel Approach for High-Quality Malcode Generationaccepted
Learning to Align: Addressing Character Frequency Distribution Shifts in Handwritten Text Recognitionaccepted
Learning to Ask: When LLM Agents Meet Unclear Instructionaccepted
Learning to Describe Implicit Changes: Noise-robust Pre-training for Image Difference Captioningaccepted
Learning to Instruct: Fine-Tuning a Task-Aware Instruction Optimizer for Black-Box LLMsaccepted
Learning to See through Sound: From VggCaps to Multi2Cap for Richer Automated Audio Captioningaccepted
Legal Fact Prediction: The Missing Piece in Legal Judgment Predictionaccepted
Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learningaccepted
LegalSearchLM: Rethinking Legal Case Retrieval as Legal Elements Generationaccepted
LegoSLM: Connecting LLM with Speech Encoder using CTC Posteriorsaccepted
Lemma Dilemma: On Lemma Generation Without Domain- or Language-Specific Training Dataaccepted
Lemmatization as a Classification Task: Results from Arabic across Multiple Genresaccepted
Lemmatization of Polish Multi-word Expressionsaccepted
Length Representations in Large Language Modelsaccepted
Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinionsaccepted
Less Is MuRE: Revisiting Shallow Knowledge Graph Embeddingsaccepted
Less is More: The Effectiveness of Compact Typological Language Representationsaccepted
Let Them Down Easy! Contextual Effects of LLM Guardrails on User Perceptions and Preferencesaccepted
Let’s Play Across Cultures: A Large Multilingual, Multicultural Benchmark for Assessing Language Models’ Understanding of Sportsaccepted
Let’s Reason Formally: Natural-Formal Hybrid Reasoning Enhances LLM’s Math Capabilityaccepted
Leveraging 3D Gaussian for Temporal Knowledge Graph Embeddingaccepted
Leveraging Cognitive Complexity of Texts for Contextualization in Dense Retrievalaccepted
Leveraging High-Resource English Corpora for Cross-lingual Domain Adaptation in Low-Resource Japanese Medicine via Continued Pre-trainingaccepted
Leveraging Knowledge Graph-Enhanced LLMs for Context-Aware Medical Consultationaccepted
Leveraging Large Models to Evaluate Novel Content: A Case Study on Advertisement Creativityaccepted
Leveraging Loanword Constraints for Improving Machine Translation in a Low-Resource Multilingual Contextaccepted
Leveraging Multilingual Training for Authorship Representation: Enhancing Generalization across Languages and Domainsaccepted
Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guaranteesaccepted
Leveraging Text-to-Text Transformers as Classifier Chain for Few-Shot Multi-Label Classificationaccepted
Leveraging Unpaired Feedback for Long-Term LLM-based Recommendation Tuningaccepted
Leveraging What’s Overfixed: Post-Correction via LLM Grammatical Error Overcorrectionaccepted
Leveraging the Cross-Domain & Cross-Linguistic Corpus for Low Resource NMT: A Case Study On Bhili-Hindi-English Parallel Corpusaccepted
LexTime: A Benchmark for Temporal Ordering of Legal Eventsaccepted
LiTEx: A Linguistic Taxonomy of Explanations for Understanding Within-Label Variation in Natural Language Inferenceaccepted
LiTransProQA: An LLM-based Literary Translation Evaluation Metric with Professional Question Answeringaccepted
Liaozhai through the Looking-Glass: On Paratextual Explicitation of Culture-Bound Terms in Machine Translationaccepted
Lifelong Knowledge Editing requires Better Regularizationaccepted
LightRAG: Simple and Fast Retrieval-Augmented Generationaccepted
LightThinker: Thinking Step-by-Step Compressionaccepted
Likelihood Variance as Text Importance for Resampling Texts to Map Language Modelsaccepted
LimRank: Less is More for Reasoning-Intensive Information Rerankingaccepted
LimaCost: Data Valuation for Instruction Tuning of Large Language Modelsaccepted
Linear Steerability in Language Models: When It Emerges and How It Evolvesaccepted
Linear-Time Demonstration Selection for In-Context Learning via Gradient Estimationaccepted
LingGym: How Far Are LLMs from Thinking Like Field Linguists?accepted
LinguaLens: Towards Interpreting Linguistic Mechanisms of Large Language Models via Sparse Auto-Encoderaccepted
Linguistic Alignment Predicts Learning in Small Group Tutoring Sessionsaccepted
Linguistic Neuron Overlap Patterns to Facilitate Cross-lingual Transfer on Low-resource Languagesaccepted
Linguistic and Embedding-Based Profiling of Texts Generated by Humans and Large Language Modelsaccepted
Linguistically-Controlled Paraphrase Generationaccepted
LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLaccepted
LiteASR: Efficient Automatic Speech Recognition with Low-Rank Approximationaccepted
LiteraryQA: Towards Effective Evaluation of Long-document Narrative QAaccepted
LlmFixer: Fix the Helpfulness of Defensive Large Language Modelsaccepted
LoCt-Instruct: An Automatic Pipeline for Constructing Datasets of Logical Continuous Instructionsaccepted
LoRA-MGPO: Mitigating Double Descent in Low-Rank Adaptation via Momentum-Guided Perturbation Optimizationaccepted
LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuningaccepted
LoRACoE: Improving Large Language Model via Composition-based LoRA Expertaccepted
LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystemaccepted
LoRE-Merging: Exploring Low-Rank Estimation For Large Language Model Mergingaccepted
LoRaDA: Low-Rank Direct Attention Adaptation for Efficient LLM Fine-tuningaccepted
LoSiA: Efficient High-Rank Fine-Tuning via Subnet Localization and Optimizationaccepted
Local Normalization Distortion and the Thermodynamic Formalism of Decoding Strategies for Large Language Modelsaccepted
Localizing Malicious Outputs from CodeLLMaccepted
Locate-then-Merge: Neuron-Level Parameter Fusion for Mitigating Catastrophic Forgetting in Multimodal LLMsaccepted
Lock on Target! Precision Unlearning via Directional Controlaccepted
LogiCoL: Logically-Informed Contrastive Learning for Set-based Dense Retrievalaccepted
LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoningaccepted
Logic-Thinker: Teaching Large Language Models to Think more Logically.accepted
Logic: Long-form Outline Generation via Imitative and Critical Self-refinementaccepted
LogicTree: Structured Proof Exploration for Coherent and Rigorous Logical Reasoning with Large Language Modelsaccepted
Logical Reasoning with Outcome Reward Models for Test-Time Scalingaccepted
Logit Space Constrained Fine-Tuning for Mitigating Hallucinations in LLM-Based Recommender Systemsaccepted
Logits-Based Finetuningaccepted
Logos as a Well-Tempered Pre-train for Sign Language Recognitionaccepted
Long Chain-of-Thought Fine-tuning via Understanding-to-Reasoning Transitionaccepted
Long-Form Information Alignment Evaluation Beyond Atomic Factsaccepted
Long-context Language Models Fail in Basic Retrieval Tasks Without Sufficient Reasoning Stepsaccepted
LongLLaVA: Scaling Multi-modal LLMs to 1000 Images Efficiently via a Hybrid Architectureaccepted
LongTableBench: Benchmarking Long-Context Table Reasoning across Real-World Formats and Domainsaccepted
LongTail-Swap: benchmarking language models’ abilities on rare wordsaccepted
LongWeave: A Long-Form Generation Benchmark Bridging Real-World Relevance and Verifiabilityaccepted
Look Again, Think Slowly: Enhancing Visual Reflection in Vision-Language Modelsaccepted
Look Beyond Feeling: Unveiling Latent Needs from Implicit Expressions for Proactive Emotional Supportaccepted
Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Queryaccepted
Looking Beyond Text: Reducing Language Bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidanceaccepted
Looking Beyond the Pixels: Evaluating Visual Metaphor Understanding in VLMsaccepted
Lost in Embeddings: Information Loss in Vision–Language Modelsaccepted
Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuningaccepted
Low-Hallucination and Efficient Coreference Resolution with LLMsaccepted
Low-Resource Languages LLM Disinformation is Within Reach: The Case of Walliserdeutschaccepted
LyapLock: Bounded Knowledge Preservation in Sequential Large Language Model Editingaccepted
M-ABSA: A Multilingual Dataset for Aspect-Based Sentiment Analysisaccepted
M-BRe: Discovering Training Samples for Relation Extraction from Unlabeled Texts with Large Language Modelsaccepted
M-Help: Using Social Media Data to Detect Mental Health Help-Seeking Signalsaccepted
M-LongDoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Frameworkaccepted
M-Ped: Multi-Prompt Ensemble Decoding for Large Language Modelsaccepted
M-Wanda: Improving One-Shot Pruning for Multilingual LLMsaccepted
M2Edit: Locate and Edit Multi-Granularity Knowledge in Multimodal Large Language Modelaccepted
M3Retrieve: Benchmarking Multimodal Retrieval for Medicineaccepted
MA-DPR: Manifold-aware Distance Metrics for Dense Passage Retrievalaccepted
MA-GTS: A Multi-Agent Framework for Solving Complex Graph Problems in Real-World Applicationsaccepted
MAC-Tuning: LLM Multi-Compositional Problem Reasoning with Enhanced Knowledge Boundary Awarenessaccepted
MADAWSD: Multi-Agent Debate Framework for Adversarial Word Sense Disambiguationaccepted
MADD: Multi-Agent Drug Discovery Orchestraaccepted
MAFMO: Multi-modal Adaptive Fusion with Meta-template Optimization for Vision-Language Modelsaccepted
MAGIC: A Multi-Hop and Graph-Based Benchmark for Inter-Context Conflicts in Retrieval-Augmented Generationaccepted
MAIN: Mutual Alignment Is Necessary for instruction tuningaccepted
MAKAR: a Multi-Agent framework based Knowledge-Augmented Reasoning for Grounded Multimodal Named Entity Recognitionaccepted
MAKIEval: A Multilingual Automatic WiKidata-based Framework for Cultural Awareness Evaluation for LLMsaccepted
MANTA: A Scalable Pipeline for Transmuting Massive Web Corpora into Instruction Datasetsaccepted
MARIO-0.5B: A Multi-Agent Lightweight Model for Real-Time Open Information Extraction in Low-Resource Settingsaccepted
MARS-Bench: A Multi-turn Athletic Real-world Scenario Benchmark for Dialogue Evaluationaccepted
MASSIVE-Agents: A Benchmark for Multilingual Function-Calling in 52 Languagesaccepted
MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language Modelsaccepted
MASTER: Multi-Agent Security Through Exploration of Roles and Topological Structures - A Comprehensive Frameworkaccepted
MATCH: Task-Driven Code Evaluation through Contrastive Learningaccepted
MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translationaccepted
MAgICoRe: Multi-Agent, Iterative, Coarse-to-Fine Refinement for Reasoningaccepted
MAviS: A Multimodal Conversational Assistant For Avian Speciesaccepted
MC2: A Minimum-Coverage and Dataset-Agnostic Framework for Compositional Generalization of LLMs on Semantic Parsingaccepted
MCIP: Protecting MCP Safety via Model Contextual Integrity Protocolaccepted
MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Searchaccepted
MCiteBench: A Multimodal Benchmark for Generating Text with Citationsaccepted
MDSEval: A Meta-Evaluation Benchmark for Multimodal Dialogue Summarizationaccepted
MEBench: Benchmarking Large Language Models for Cross-Document Multi-Entity Question Answeringaccepted
MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapperaccepted
MERMAID: Multi-perspective Self-reflective Agents with Generative Augmentation for Emotion Recognitionaccepted
METok: Multi-Stage Event-based Token Compression for Efficient Long Video Understandingaccepted
MEXA: Towards General Multimodal Reasoning with Dynamic Multi-Expert Aggregationaccepted
MFTCXplain: A Multilingual Benchmark Dataset for Evaluating the Moral Reasoning of LLMs through Multi-hop Hate Speech Explanationaccepted
MIND: Towards Immersive Psychological Healing with Multi-Agent Inner Dialogueaccepted
MIO: A Foundation Model on Multimodal Tokensaccepted
MIRROR: Multimodal Cognitive Reframing Therapy for Rolling with Resistanceaccepted
ML-Promise: A Multilingual Dataset for Corporate Promise Verificationaccepted
MLAlgo-Bench: Can Machines Implement Machine Learning Algorithms?accepted
MLWQ: Efficient Small Language Model Deployment via Multi-Level Weight Quantizationaccepted
MM-CRITIC: A Holistic Evaluation of Large Multimodal Models as Multimodal Critiqueaccepted
MMA: Cross-Domain Knowledge Integration via Mixture of Multi-Domain Agentsaccepted
MMAG: Multimodal Learning for Mucus Anomaly Grading in Nasal Endoscopy via Semantic Attribute Promptingaccepted
MMAPG: A Training-Free Framework for Multimodal Multi-hop Question Answering via Adaptive Planning Graphsaccepted
MMDocIR: Benchmarking Multimodal Retrieval for Long Documentsaccepted
MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluationaccepted
MMPlanner: Zero-Shot Multimodal Procedural Planning with Chain-of-Thought Object State Reasoningaccepted
MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?accepted
MOLE: Metadata Extraction and Validation in Scientific Papers Using LLMsaccepted
MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devicesaccepted
MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulationsaccepted
MPCG: Multi-Round Persona-Conditioned Generation for Modeling the Evolution of Misinformation with LLMsaccepted
MPO: Boosting LLM Agents with Meta Plan Optimizationaccepted
MPRF: Interpretable Stance Detection through Multi-Path Reasoning Frameworkaccepted
MPTA: MultiTask Personalization Assessmentaccepted
MR. Judge: Multimodal Reasoner as a Judgeaccepted
MRAG: A Modular Retrieval Framework for Time-Sensitive Question Answeringaccepted
MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMsaccepted
MS-RAG: Simple and Effective Multi-Semantic Retrieval-Augmented Generationaccepted
MT-Mol: Multi Agent System with Tool-based Reasoning for Molecular Optimizationaccepted
MT-R1-Zero: Advancing LLM-based Machine Translation via R1-Zero-like Reinforcement Learningaccepted
MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modelingaccepted
MTabVQA: Evaluating Multi-Tabular Reasoning of Language Models in Visual Spaceaccepted
MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Modelsaccepted
MUG-Eval: A Proxy Evaluation Framework for Multilingual Generation Capabilities in Any Languageaccepted
MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalitiesaccepted
MULTITAT: Benchmarking Multilingual Table-and-Text Question Answeringaccepted
MULTIVOX: A Benchmark for Evaluating Voice Assistants for Multimodal Interactionsaccepted
MUSE: MCTS-Driven Red Teaming Framework for Enhanced Multi-Turn Dialogue Safety in Large Language Modelsaccepted
MUZO: Leveraging Multiple Queries and Momentum for Zeroth-Order Fine-Tuning of Large Language Modelsaccepted
MV-CLAM: Multi-View Molecular Interpretation with Cross-Modal Projection via Language Modelaccepted
MaGiX: A Multi-Granular Adaptive Graph Intelligence Framework for Enhancing Cross-Lingual RAGaccepted
MaZO: Masked Zeroth-Order Optimization for Multi-Task Fine-Tuning of Large Language Modelsaccepted
Machine-generated text detection prevents language model collapseaccepted
Mahānāma: A Unique Testbed for Literary Entity Discovery and Linkingaccepted
Make Every Letter Count: Building Dialect Variation Dictionaries from Monolingual Corporaaccepted
Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalizationaccepted
Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoningaccepted
Mamba Drafters for Speculative Decodingaccepted
ManuSearch: Democratizing Deep Search in Large Language Models with a Transparent and Open Multi-Agent Frameworkaccepted
Mapping Toxic Comments Across Demographics: A Dataset from German Public Broadcastingaccepted
Mapping semantic networks to Dutch word embeddings as a diagnostic tool for cognitive declineaccepted
Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMsaccepted
MarathiEmoExplain: A Dataset for Sentiment, Emotion, and Explanation in Low-Resource Marathiaccepted
MaskCD: Mitigating LVLM Hallucinations by Image Head Masked Contrastive Decodingaccepted
Masked Diffusion Captioning for Visual Feature Learningaccepted
Massive Supervised Fine-tuning Experiments Reveal How Data, Layer, and Training Factors Shape LLM Alignment Qualityaccepted
MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutorsaccepted
Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Scienceaccepted
Measuring Bias or Measuring the Task: Understanding the Brittle Nature of LLM Gender Biasesaccepted
Measuring Chain of Thought Faithfulness by Unlearning Reasoning Stepsaccepted
Measuring Lexical Diversity of Synthetic Data Generated through Fine-Grained Persona Promptingaccepted
Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmarkaccepted
Measuring Sycophancy of Language Models in Multi-turn Dialoguesaccepted
Measuring and Mitigating Media Outlet Name Bias in Large Language Modelsaccepted
Measuring scalar constructs in social science with LLMsaccepted
Measuring the Effect of Disfluency in Multilingual Knowledge Probing Benchmarksaccepted
Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluationsaccepted
Mechanistic Understanding and Mitigation of Language Confusion in English-Centric Large Language Modelsaccepted
Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewardsaccepted
Med-VRAgent: A Framework for Medical Visual Reasoning-Enhanced Agentsaccepted
MedCOD: Enhancing English-to-Spanish Medical Translation of Large Language Models Using Enriched Chain-of-Dictionary Frameworkaccepted
MedEBench: Diagnosing Reliability in Text-Guided Medical Image Editingaccepted
MedFact: A Large-scale Chinese Dataset for Evidence-based Medical Fact-checking of LLM Responsesaccepted
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Modelsaccepted
MedLinkDE – MedDRA Entity Linking for German with Guided Chain of Thought Reasoningaccepted
MediVLM: A Vision Language Model for Radiology Report Generation from Medical Imagesaccepted
Media Source Matters More Than Content: Unveiling Political Bias in LLM-Generated Citationsaccepted
MemInsight: Autonomous Memory Augmentation for LLM Agentsaccepted
Membership and Memorization in LLM Knowledge Distillationaccepted
MemeArena: Automating Context-Aware Unbiased Evaluation of Harmfulness Understanding for Multimodal Large Language Modelsaccepted
MemeIntel: Explainable Detection of Propagandistic and Hateful Memesaccepted
MemeInterpret: Towards an All-in-One Dataset for Meme Understandingaccepted
MemeReaCon: Probing Contextual Meme Understanding in Large Vision-Language Modelsaccepted
Memorization or Reasoning? Exploring the Idiom Understanding of LLMsaccepted
Memorization ≠ Understanding: Do Large Language Models Have the Ability of Scenario Cognition?accepted
Memory OS of AI Agentaccepted
Memory-QA: Answering Recall Questions Based on Multimodal Memoriesaccepted
Memory-enhanced Large Language Model for Cross-lingual Dependency Parsing via Deep Hierarchical Syntax Understandingaccepted
MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Mediaaccepted
Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMsaccepted
Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Mergingaccepted
MessIRve: A Large-Scale Spanish Information Retrieval Datasetaccepted
Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judgeaccepted
Meta-Semantics Augmented Few-Shot Relational Learningaccepted
MetaFaith: Faithful Natural Language Uncertainty Expression in LLMsaccepted
MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transferaccepted
MetaMixSpeech: Meta Task Augmentation for Low-Resource Speech Recognitionaccepted
Metric Calculating Benchmark: Code-Verifiable Complicate Instruction Following Benchmark for Large Language Modelsaccepted
MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learningaccepted
MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queriesaccepted
MicroEdit: Neuron-level Knowledge Disentanglement and Localization in Lifelong Model Editingaccepted
MidPO: Dual Preference Optimization for Safety and Helpfulness in Large Language Models via a Mixture of Experts Frameworkaccepted
Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learningaccepted
Mind the Blind Spots: A Focus-Level Evaluation Framework for LLM Reviewsaccepted
Mind the Dialect: NLP Advancements Uncover Fairness Disparities for Arabic Users in Recommendation Systemsaccepted
Mind the Gap: A Closer Look at Tokenization for Multiple-Choice Question Answering with LLMsaccepted
Mind the Gap: How BabyLMs Learn Filler-Gap Dependenciesaccepted
Mind the Inclusivity Gap: Multilingual Gender-Neutral Translation Evaluation with mGeNTEaccepted
Mind the Style Gap: Meta-Evaluation of Style and Attribute Transfer Metricsaccepted
Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?accepted
Minimal Ranks, Maximum Confidence: Parameter-efficient Uncertainty Quantification for LoRAaccepted
Minimal, Local, and Robust: Embedding-Only Edits for Implicit Bias in T2I Modelsaccepted
Mining the Past with Dual Criteria: Integrating Three types of Historical Information for Context-aware Event Forecastingaccepted
Misalignment Attack on Text-to-Image Models via Text Embedding Optimization and Inversionaccepted
MisinfoBench: A Multi-Dimensional Benchmark for Evaluating LLMs’ Resilience to Misinformationaccepted
Mitigate One, Skew Another? Tackling Intersectional Biases in Text-to-Image Modelsaccepted
Mitigating Attention Localization in Small Scale: Self-Attention Refinement via One-step Belief Propagationaccepted
Mitigating Biases in Language Models via Bias Unlearningaccepted
Mitigating Catastrophic Forgetting in Large Language Models with Forgetting-aware Pruningaccepted
Mitigating Gender Bias via Fostering Exploratory Thinking in LLMsaccepted
Mitigating Geospatial Knowledge Hallucination in Large Language Models: Benchmarking and Dynamic Factuality Aligningaccepted
Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flowaccepted
Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNetsaccepted
Mitigating Hallucinations in Large Vision-Language Models by Self-Injecting Hallucinationsaccepted
Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimizationaccepted
Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppressionaccepted
Mitigating Interviewer Bias in Multimodal Depression Detection: An Approach with Adversarial Learning and Contextual Positional Encodingaccepted
Mitigating Object Hallucinations in MLLMs via Multi-Frequency Perturbationsaccepted
Mitigating Sequential Dependencies: A Survey of Algorithms and Systems for Generation-Refinement Frameworks in Autoregressive Modelsaccepted
Mitigating Spurious Correlations via Counterfactual Contrastive Learningaccepted
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descentaccepted
Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Dataaccepted
MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corporaaccepted
Mixed Signals: Decoding VLMs’ Reasoning and Underlying Bias in Vision-Language Conflictaccepted
Mixing Inference-time Experts for Enhancing LLM Reasoningaccepted
Mixture of Languages: Improved Multilingual Encoders Through Language Groupingaccepted
Mixture of Length and Pruning Experts for Knowledge Graphs Reasoningaccepted
Mixture of LoRA Experts for Continual Information Extraction with LLMsaccepted
Mixture of Weight-shared Heterogeneous Group Attention Experts for Dynamic Token-wise KV Optimizationaccepted
Mixture-of-Clustered-Experts: Advancing Expert Specialization and Generalization in Instruction Tuningaccepted
MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrievalaccepted
MoMentS: A Comprehensive Multimodal Benchmark for Theory of Mindaccepted
MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governanceaccepted
MoR: Better Handling Diverse Queries with a Mixture of Sparse, Dense, and Human Retrieversaccepted
MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Languageaccepted
MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional Thresholdsaccepted
MoVa: Towards Generalizable Classification of Human Morals and Valuesaccepted
MoVoC: Morphology-Aware Subword Construction for Ge’ez Script Languagesaccepted
MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Enginesaccepted
ModRWKV: Transformer Multimodality in Linear Timeaccepted
ModalPrompt: Towards Efficient Multimodal Continual Instruction Tuning with Dual-Modality Guided Promptaccepted
Model Calibration for Emotion Detectionaccepted
Model Consistency as a Cheap yet Predictive Proxy for LLM Elo Scoresaccepted
Model Unlearning via Sparse Autoencoder Subspace Guided Projectionsaccepted
Model-Based Ranking of Source Languages for Zero-Shot Cross-Lingual Transferaccepted
Model-based Large Language Model Customization as Serviceaccepted
ModelCitizens: Representing Community Voices in Online Safetyaccepted
Modeling Bottom-up Information Quality during Language Processingaccepted
Modeling Subjectivity in Cognitive Appraisal with Language Modelsaccepted
Modeling, Evaluating, and Embodying Personality in LLMs: A Surveyaccepted
ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challengesaccepted
MolErr2Fix: Benchmarking LLM Trustworthiness in Chemistry via Modular Error Detection, Localization, Explanation, and Correctionaccepted
Molecular String Representation Preferences in Pretrained LLMs: A Comparative Study in Zero- & Few-Shot Molecular Property Predictionaccepted
Mondrian: A Framework for Logical Abstract (Re)Structuringaccepted
Morables: A Benchmark for Assessing Abstract Moral Reasoning in LLMs with Fablesaccepted
Moral Framing in Politics (MFiP): A new resource and models for moral framingaccepted
More Documents, Same Length: Isolating the Challenge of Multiple Documents in RAGaccepted
More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compressionaccepted
Morpheme Induction for Emergent Languageaccepted
MotivGraph-SoIQ: Integrating Motivational Knowledge Graphs and Socratic Dialogue for Enhanced LLM Ideationaccepted
MovieCORE: COgnitive REasoning in Moviesaccepted
MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safetyaccepted
MuCAL: Contrastive Alignment for Preference-Driven KG-to-Text Generationaccepted
MuTIS: Enhancing Reasoning Efficiency through Multi Turn Intervention Sampling in Reinforcement Learningaccepted
Multi-Agent Autonomous Driving Systems with Large Language Models: A Survey of Recent Advances, Resources, and Future Directionsaccepted
Multi-Document Event Extraction Using Large and Small Language Modelsaccepted
Multi-Domain Explainability of Preferencesaccepted
Multi-Frequency Contrastive Decoding: Alleviating Hallucinations for Large Vision-Language Modelsaccepted
Multi-LMentry: Can Multilingual LLMs Solve Elementary Tasks Across Languages?accepted
Multi-Modal Framing Analysis of Newsaccepted
Multi-Surrogate-Objective Optimization for Neural Topic Modelsaccepted
Multi-level Diagnosis and Evaluation for Robust Tabular Feature Engineering with Large Language Modelsaccepted
Multi-perspective Analysis of Large Language Model Domain Specialization: An Experiment in Accounting Audit Procedures Generationaccepted
Multi-token Mask-filling and Implicit Discourse Relationsaccepted
Multi-view-guided Passage Reranking with Large Language Modelsaccepted
MultiAgentESC: A LLM-based Multi-Agent Collaboration Framework for Emotional Support Conversationaccepted
MultiClaimNet: A Massively Multilingual Dataset of Fact-Checked Claim Clustersaccepted
MultiConIR: Towards Multi-Condition Information Retrievalaccepted
MultiDocFusion : Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documentsaccepted
MultiLingPoT: Boosting Mathematical Reasoning in LLMs through Multilingual Program Integrationaccepted
MultiLogicNMR(er): A Benchmark and Neural-Symbolic Framework for Non-monotonic Reasoning with Multiple Extensionsaccepted
MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classificationaccepted
MultiMed-ST: Large-scale Many-to-many Multilingual Medical Speech Translationaccepted
MultiPL-MoE: Multi-Programming-Lingual Extension of Large Language Models through Hybrid Mixture-of-Expertsaccepted
Multifaceted Evaluation of Audio-Visual Capability for MLLMs: Effectiveness, Efficiency, Generalizability and Robustnessaccepted
Multilingual Collaborative Defense for Large Language Modelsaccepted
Multilingual Data Filtering using Synthetic Data from Large Language Modelsaccepted
Multilingual Datasets for Custom Input Extraction and Explanation Requests Parsing in Conversational XAI Systemsaccepted
Multilingual Dialogue Generation and Localization with Dialogue Act Scriptingaccepted
Multilingual Federated Low-Rank Adaptation for Collaborative Content Anomaly Detection across Multilingual Social Media Participantsaccepted
Multilingual Generative Retrieval via Cross-lingual Semantic Compressionaccepted
Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharingaccepted
Multilingual Language Model Pretraining using Machine-translated Dataaccepted
Multilingual Pretraining for Pixel Language Modelsaccepted
Multilingual Prompting for Improving LLM Generation Diversityaccepted
Multilingual Verbalisation of Knowledge Graphsaccepted
Multilingual vs Crosslingual Retrieval of Fact-Checked Claims: A Tale of Two Approachesaccepted
Multilinguality Does not Make Sense: Investigating Factors Behind Zero-Shot Cross-Lingual Transfer in Sense-Aware Tasksaccepted
Multimedia Event Extraction with LLM Knowledge Editingaccepted
Multimodal Document-level Triple Extraction via Dynamic Graph Enhancement and Relation-Aware Reflectionaccepted
Multimodal Emotion Recognition in Conversations: A Survey of Methods, Trends, Challenges and Prospectsaccepted
Multimodal Fine-grained Context Interaction Graph Modeling for Conversational Speech Synthesisaccepted
Multimodal Language Models See Better When They Look Shalloweraccepted
Multimodal Neural Machine Translation: A Survey of the State of the Artaccepted
Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Oddaccepted
MusKGC: A Flexible Multi-source Knowledge Enhancement Framework for Open-World Knowledge Graph Completionaccepted
MuseScorer: Idea Originality Scoring At Scaleaccepted
MythTriage: Scalable Detection of Opioid Use Disorder Myths on a Video-Sharing Platformaccepted
N-CORE: N-View Consistency Regularization for Disentangled Representation Learning in Nonverbal Vocalizationsaccepted
NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Humanaccepted
NER Retriever: Zero-Shot Named Entity Retrieval with Type-Aware Embeddingsaccepted
NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Callsaccepted
NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaksaccepted
NILE: Internal Consistency Alignment in Large Language Modelsaccepted
NIM: Neuro-symbolic Ideographic Metalanguage for Inclusive Communicationaccepted
NL-Debugging: Exploiting Natural Language as an Intermediate Representation for Code Debuggingaccepted
NL2Lean: Translating Natural Language into Lean 4 through Multi-Aspect Reinforcement Learningaccepted
NLKI: A Lightweight Natural Language Knowledge Integration Framework for Improving Small VLMs in Commonsense VQA Tasksaccepted
NLP Needs Diversity outside of ‘Diversity’accepted
NLP-ADBench: NLP Anomaly Detection Benchmarkaccepted
NLoRA: Nyström-Initiated Low-Rank Adaptation for Large Language Modelsaccepted
NOVA-63: Native Omni-lingual Versatile Assessments of 63 Disciplinesaccepted
NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learningaccepted
NUMINA: A Natural Understanding Benchmark for Multi-dimensional Intelligence and Numerical Reasoning Abilitiesaccepted
NUTMEG: Separating Signal From Noise in Annotator Disagreementaccepted
NarratEX Dataset: Explaining the Dominant Narratives in News Textsaccepted
Natural Context Drift Undermines the Natural Language Understanding of Large Language Modelsaccepted
Navigating the Unknown: Intent Classification and Out-of-Distribution Detection Using Large Language Modelsaccepted
NeLLCom-Lex: A Neural-agent Framework to Study the Interplay between Lexical Systems and Language Useaccepted
NeighXLM: Enhancing Cross-Lingual Transfer in Low-Resource Languages via Neighbor-Augmented Contrastive Pretrainingaccepted
Nested Named Entity Recognition as Single-Pass Sequence Labelingaccepted
Neural Topic Modeling via Contextual and Graph Information Fusionaccepted
NeuroAda: Activating Each Neuron’s Potential for Parameter-Efficient Fine-Tuningaccepted
Neuron-Level Differentiation of Memorization and Generalization in Large Language Modelsaccepted
Neutral Is Not Unbiased: Evaluating Implicit and Intersectional Identity Bias in LLMs Through Structured Narrative Scenariosaccepted
Nexus: Adaptive Upcycling to Efficiently Pretrain Mixture of Expertsaccepted
NileChat: Towards Linguistically Diverse and Culturally Aware LLMs for Local Communitiesaccepted
Nine Ways to Break Copyright Law and Why Our LLM Won’t: A Fair Use Aligned Generation Frameworkaccepted
NitiBench: Benchmarking LLM Frameworks on Thai Legal Question Answering Capabilitiesaccepted
No Black Boxes: Interpretable and Interactable Predictive Healthcare with Knowledge-Enhanced Agentic Causal Discoveryaccepted
No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Usersaccepted
No Need for Explanations: LLMs can implicitly learn from mistakes in-contextaccepted
Noise, Adaptation, and Strategy: Assessing LLM Fidelity in Decision-Makingaccepted

EMNLP accepted papers in other years

EMNLP 2024 (2,379)EMNLP 2023 (2,009)EMNLP 2022 (1,439)EMNLP 2021 (1,311)

Looking for submission deadlines instead? See the conference deadline calendar.