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

Non-Existent Relationship: Fact-Aware Multi-Level Machine-Generated Text Detectionaccepted
NormAL LoRA: What is the perfect size?accepted
NormGenesis: Multicultural Dialogue Generation via Exemplar-Guided Social Norm Modeling and Violation Recoveryaccepted
NormXLogit: The Head-on-Top Never Liesaccepted
Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Modelsaccepted
Not All Options Are Created Equal: Textual Option Weighting for Token-Efficient LLM-Based Knowledge Tracingaccepted
Not All Parameters Are Created Equal: Smart Isolation Boosts Fine-Tuning Performanceaccepted
Not All Voices Are Rewarded Equally: Probing and Repairing Reward Models across Human Diversityaccepted
Not Every Token Needs Forgetting: Selective Unlearning Balancing Forgetting and Utility in Large Language Modelsaccepted
Not Lost After All: How Cross-Encoder Attribution Challenges Position Bias Assumptions in LLM Summarizationaccepted
Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Lossaccepted
Not Your Typical Government Tipline: LLM-Assisted Routing of Environmental Protection Agency Citizen Tipsaccepted
Not-Just-Scaling Laws: Towards a Better Understanding of the Downstream Impact of Language Model Design Decisionsaccepted
NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contextsaccepted
Nullspace Disentanglement for Red Teaming Language Modelsaccepted
OAgents: An Empirical Study of Building Effective Agentsaccepted
OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Modelsaccepted
OG-RAG: Ontology-grounded retrieval-augmented generation for large language modelsaccepted
OMS: On-the-fly, Multi-Objective, Self-Reflective Ad Keyword Generation via LLM Agentaccepted
ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusionaccepted
ORPP: Self-Optimizing Role-playing Prompts to Enhance Language Model Capabilitiesaccepted
OSC: Cognitive Orchestration through Dynamic Knowledge Alignment in Multi-Agent LLM Collaborationaccepted
OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption Modelsaccepted
OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literatureaccepted
O_O-VC: Synthetic Data-Driven One-to-One Alignment for Any-to-Any Voice Conversionaccepted
Offloaded Reasoning: Efficient Inference for Large Language Models via Modular Reasoning and Refinementaccepted
OkraLong: A Flexible Retrieval-Augmented Framework for Long-Text Question Answeringaccepted
OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domainaccepted
OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinkingaccepted
On Collaborating Small and Large Models For Few-shot Intent Detectionaccepted
On Domain-Adaptive Post-Training for Multimodal Large Language Modelsaccepted
On Guardrail Models’ Robustness to Mutations and Adversarial Attacksaccepted
On LLM-Based Scientific Inductive Reasoning Beyond Equationsaccepted
On Pruning State-Space LLMsaccepted
On Relation-Specific Neurons in Large Language Modelsaccepted
On the Correspondence between the Squared Norm and Information Content in Text Embeddingsaccepted
On the Effectiveness of Prompt-Moderated LLMs for Math Tutoring at the Tertiary Levelaccepted
On the Fine-Grained Planning Abilities of VLM Web Agentsaccepted
On the Perception Bottleneck of VLMs for Chart Understandingaccepted
On the Role of Entity and Event Level Conceptualization in Generalizable Reasoning: A Survey of Tasks, Methods, Applications, and Future Directionsaccepted
On the Role of Model Prior in Real-World Inductive Reasoningaccepted
On the Same Wavelength? Evaluating Pragmatic Reasoning in Language Models across Broad Conceptsaccepted
On the Versatility of Sparse Autoencoders for In-Context Learningaccepted
One More Modality: Does Abstract Meaning Representation Benefit Visual Question Answering?accepted
One More Question is Enough, Expert Question Decomposition (EQD) Model for Domain Quantitative Reasoningaccepted
One Planner To Guide Them All ! Learning Adaptive Conversational Planners for Goal-oriented Dialoguesaccepted
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systemsaccepted
OntologyRAG-Q: Resource Development and Benchmarking for Retrieval-Augmented Question Answering in Qur’anic Tafsiraccepted
Open-DeBias: Toward Mitigating Open-Set Bias in Language Modelsaccepted
OpenNER 1.0: Standardized Open-Access Named Entity Recognition Datasets in 50+ Languagesaccepted
OpenTuringBench: An Open-Model-based Benchmark and Framework for Machine-Generated Text Detection and Attributionaccepted
OptiSeq: Ordering Examples On-The-Fly for In-Context Learningaccepted
Optimising Factual Consistency in Summarisation via Preference Learning from Multiple Imperfect Metricsaccepted
Optimizing Cross-Client Domain Coverage for Federated Instruction Tuning of Large Language Modelsaccepted
Orchestrating Audio: Multi-Agent Framework for Long-Video Audio Synthesisaccepted
Order Doesn’t Matter, But Reasoning Does: Training LLMs with Order-Centric Augmentationaccepted
Orthogonal Finetuning Made Scalableaccepted
Out of Sight, Not Out of Context? Egocentric Spatial Reasoning in VLMs Across Disjoint Framesaccepted
Out-of-Context Reasoning in Large Language Modelsaccepted
Over-Generation and Compaction: A Prompting Strategy for Procedural Text Adaptation with Large Language Modelsaccepted
Overcoming Black-box Attack Inefficiency with Hybrid and Dynamic Select Algorithmsaccepted
P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMsaccepted
PACHAT: Persona-Aware Speech Assistant for Multi-party Dialogueaccepted
PAFT: Prompt-Agnostic Fine-Tuningaccepted
PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreementsaccepted
PAMN: Multi-phase Correlation Modeling for Contrast-Enhanced 3D Medical Image Retrievalaccepted
PATIMT-Bench: A Multi-Scenario Benchmark for Position-Aware Text Image Machine Translation in Large Vision-Language Modelsaccepted
PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximizationaccepted
PD3F: A Pluggable and Dynamic DoS-Defense Framework against resource consumption attacks targeting Large Language Modelsaccepted
PEPE: Long-context Extension for Large Language Models via Periodic Extrapolation Positional Encodingsaccepted
PERSEVAL: A Framework for Perspectivist Classification Evaluationaccepted
PICD-Instruct: A Generative Instruction Learning Framework for Few-Shot Multi-Intent Spoken Language Understandingaccepted
PIIvot: A Lightweight NLP Anonymization Framework for Question-Anchored Tutoring Dialoguesaccepted
PIP: Perturbation-based Iterative Pruning for Large Language Modelsaccepted
PLAN-TUNING: Post-Training Language Models to Learn Step-by-Step Planning for Complex Problem Solvingaccepted
PLLuM-Align: Polish Preference Dataset for Large Language Model Alignmentaccepted
PMPO: Probabilistic Metric Prompt Optimization for Small and Large Language Modelsaccepted
POINTS-Reader: Distillation-Free Adaptation of Vision-Language Models for Document Conversionaccepted
PORTS: Preference-Optimized Retrievers for Tool Selection with Large Language Modelsaccepted
POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge Distillationaccepted
POW: Political Overton Windows of Large Language Modelsaccepted
PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillationaccepted
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slidesaccepted
PREE: Towards Harmless and Adaptive Fingerprint Editing in Large Language Models via Knowledge Prefix Enhancementaccepted
PRIM: Towards Practical In-Image Multilingual Machine Translationaccepted
PRIME: Large Language Model Personalization with Cognitive Dual-Memory and Personalized Thought Processaccepted
PRINCIPLES: Synthetic Strategy Memory for Proactive Dialogue Agentsaccepted
PRISM: Efficient Long-Range Reasoning With Short-Context LLMsaccepted
PROOD: A Simple LLM Out-of-Distribution Guardrail Leveraging Response Semanticsaccepted
PSET: a Phonetics-Semantics Evaluation Testbedaccepted
PUER: Boosting Few-shot Positive-Unlabeled Entity Resolution with Reinforcement Learningaccepted
PVTNL: Prompting Vision Transformers with Natural Language for Generalizable Person Re-identificationaccepted
Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generationaccepted
PakBBQ: A Culturally Adapted Bias Benchmark for QAaccepted
PanicToCalm: A Proactive Counseling Agent for Panic Attacksaccepted
Parallel Communities Across the Surface Web and the Dark Webaccepted
Parallel Continuous Chain-of-Thought with Jacobi Iterationaccepted
ParetoRAG: Leveraging Sentence-Context Attention for Robust and Efficient Retrieval-Augmented Generationaccepted
Parrot: A Training Pipeline Enhances Both Program CoT and Natural Language CoT for Reasoningaccepted
Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languagesaccepted
PatentScore: Multi-dimensional Evaluation of LLM-Generated Patent Claimsaccepted
Path Drift in Large Reasoning Models: How First-Person Commitments Override Safetyaccepted
Path-enhanced Pre-trained Language Model for Knowledge Graph Completionaccepted
PathoHR: Hierarchical Reasoning for Vision-Language Models in Pathologyaccepted
Paths Not Taken: Understanding and Mending the Multilingual Factual Recall Pipelineaccepted
Pathway to Relevance: How Cross-Encoders Implement a Semantic Variant of BM25accepted
PathwiseRAG: Multi-Dimensional Exploration and Integration Frameworkaccepted
Pearl: A Multimodal Culturally-Aware Arabic Instruction Datasetaccepted
Permitted Knowledge Boundary: Evaluating the Knowledge-Constrained Responsiveness of Large Language Modelsaccepted
Permutative Preference Alignment from Listwise Ranking of Human Judgmentsaccepted
Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Researchaccepted
PersLLM: A Personified Training Approach for Large Language Modelsaccepted
Persona-Augmented Benchmarking: Evaluating LLMs Across Diverse Writing Stylesaccepted
PersonaGym: Evaluating Persona Agents and LLMsaccepted
Personality Matters: User Traits Predict LLM Preferences in Multi-Turn Collaborative Tasksaccepted
Personality Vector: Modulating Personality of Large Language Models by Model Mergingaccepted
Personalization up to a Point: Why Personalized Content Moderation Needs Boundaries, and How We Can Enforce Themaccepted
Personalized LLM Decoding via Contrasting Personal Preferenceaccepted
Personalized Language Models via Privacy-Preserving Evolutionary Model Mergingaccepted
Personalized Question Answering with User Profile Generation and Compressionaccepted
Personalized open world plan generation for safety-critical human centered autonomous systems: A case study on Artificial Pancreasaccepted
Perspective-driven Preference Optimization with Entropy Maximization for Diverse Argument Generationaccepted
PerspectiveMod: A Perspectivist Resource for Deliberative Moderationaccepted
Persuasion Dynamics in LLMs: Investigating Robustness and Adaptability in Knowledge and Safety with DuET-PDaccepted
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Timeaccepted
PhoniTale: Phonologically Grounded Mnemonic Generation for Typologically Distant Language Pairsaccepted
PhonoThink: Improving Large Language Models’ Reasoning on Chinese Phonological Ambiguitiesaccepted
PhysicsArena: The First Multimodal Physics Reasoning Benchmark Exploring Variable, Process, and Solution Dimensionsaccepted
Pi-SQL: Enhancing Text-to-SQL with Fine-Grained Guidance from Pivot Programming Languagesaccepted
Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysisaccepted
Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfactsaccepted
Plan Dynamically, Express Rhetorically: A Debate-Driven Rhetorical Framework for Argumentative Writingaccepted
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solvingaccepted
Planning-Aware Code Infilling via Horizon-Length Predictionaccepted
Playpen: An Environment for Exploring Learning From Dialogue Game Feedbackaccepted
Please Translate Again: Two Simple Experiments on Whether Human-Like Reasoning Helps Translationaccepted
Plugging Schema Graph into Multi-Table QA: A Human-Guided Framework for Reducing LLM Relianceaccepted
Pluralistic Alignment for Healthcare: A Role-Driven Frameworkaccepted
Plutus: Benchmarking Large Language Models in Low-Resource Greek Financeaccepted
PoSum-Bench: Benchmarking Position Bias in LLM-based Conversational Summarizationaccepted
Pointing to a Llama and Call it a Camel: On the Sycophancy of Multimodal Large Language Modelsaccepted
PolBiX: Detecting LLMs’ Political Bias in Fact-Checking through X-phemismsaccepted
Polish-English medical knowledge transfer: A new benchmark and resultsaccepted
PolitiSky24: U.S. Political Bluesky Dataset with User Stance Labelsaccepted
Polysemantic Dropout: Conformal OOD Detection for Specialized LLMsaccepted
PoseStitch-SLT: Linguistically Inspired Pose-Stitching for End-to-End Sign Language Translationaccepted
Position IDs Matter: An Enhanced Position Layout for Efficient Context Compression in Large Language Modelsaccepted
Position: LLMs Can be Good Tutors in English Educationaccepted
Post Persona Alignment for Multi-Session Dialogue Generationaccepted
Post-hoc Study of Climate Microtargeting on Social Media Ads with LLMs: Thematic Insights and Fairness Evaluationaccepted
Power doesn’t reside in size: A Low Parameter Hybrid Language Model (HLM) for Sentiment Analysis in Code-mixed dataaccepted
PrAd: Prompt Adaptive Tuning for Decoder-only Language Modelsaccepted
Pragmatic Inference Chain (PIC) Improving LLMs’ Reasoning of Authentic Implicit Toxic Languageaccepted
Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialogueaccepted
Pre-trained Language Models Learn Remarkably Accurate Representations of Numbersaccepted
Pre-trained Models Perform the Best When Token Distributions Follow Zipf’s Lawaccepted
Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignmentaccepted
PreGenie: An Agentic Framework for High-quality Visual Presentation Generationaccepted
Precise In-Parameter Concept Erasure in Large Language Modelsaccepted
Predicate-Guided Generation for Mathematical Reasoningaccepted
Predicting Language Models’ Success at Zero-Shot Probabilistic Predictionaccepted
Predicting Prosodic Boundaries for Children’s Textsaccepted
Preemptive Detection and Correction of Misaligned Actions in LLM Agentsaccepted
Prejudge-Before-Think: Enhancing Large Language Models at Test-Time by Process Prejudge Reasoningaccepted
Presumed Cultural Identity: How Names Shape LLM Responsesaccepted
PricingLogic: Evaluating LLMs Reasoning on Complex Tourism Pricing Tasksaccepted
PrimeX: A Dataset of Worldview, Opinion, and Explanationaccepted
Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Trainingaccepted
Principled Personas: Defining and Measuring the Intended Effects of Persona Prompting on Task Performanceaccepted
Prior Prompt Engineering for Reinforcement Fine-Tuningaccepted
Priority on High-Quality: Selecting Instruction Data via Consistency Verification of Noise Injectionaccepted
Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agentsaccepted
ProLongVid: A Simple but Strong Baseline for Long-context Video Instruction Tuningaccepted
ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrievalaccepted
ProReason: Multi-Modal Proactive Reasoning with Decoupled Eyesight and Wisdomaccepted
Proactive Assistant Dialogue Generation from Streaming Egocentric Videosaccepted
Proactive Hearing Assistants that Isolate Egocentric Conversationsaccepted
Proactive User Information Acquisition via Chats on User-Favored Topicsaccepted
Probabilistic Soundness Guarantees in LLM Reasoning Chainsaccepted
Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Inductionaccepted
Probing LLM World Models: Enhancing Guesstimation with Wisdom of Crowds Decodingaccepted
Probing Logical Reasoning of MLLMs in Scientific Diagramsaccepted
Probing Narrative Morals: A New Character-Focused MFT Framework for Use with Large Language Modelsaccepted
Probing Political Ideology in Large Language Models: How Latent Political Representations Generalize Across Tasksaccepted
Probing Semantic Routing in Large Mixture-of-Expert Modelsaccepted
Probing and Boosting Large Language Models Capabilities via Attention Headsaccepted
Probing for Arithmetic Errors in Language Modelsaccepted
Problem Solved? Information Extraction Design Space for Layout-Rich Documents using LLMsaccepted
ProcVQA: Benchmarking the Effects of Structural Properties in Mined Process Visualizations on Vision–Language Model Performanceaccepted
ProcWorld: Benchmarking Large Model Planning in Reachability-Constrained Environmentsaccepted
Procedural Environment Generation for Tool-Use Agentsaccepted
Process-Supervised Reinforcement Learning for Code Generationaccepted
Process-Supervised Reward Models for Verifying Clinical Note Generation: A Scalable Approach Guided by Domain Expertiseaccepted
Profiler: Black-box AI-generated Text Origin Detection via Context-aware Inference Pattern Analysisaccepted
Profiling LLM’s Copyright Infringement Risks under Adversarial Persuasive Promptingaccepted
Program of Thoughts for Financial Reasoning: Leveraging Dynamic In-Context Examples and Generative Retrievalaccepted
Progressive Facial Granularity Aggregation with Bilateral Attribute-based Enhancement for Face-to-Speech Synthesisaccepted
Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queriesaccepted
PromptKeeper: Safeguarding System Prompts for LLMsaccepted
Promptception: How Sensitive Are Large Multimodal Models to Prompts?accepted
PropRAG: Guiding Retrieval with Beam Search over Proposition Pathsaccepted
PropXplain: Can LLMs Enable Explainable Propaganda Detection?accepted
Protein Large Language Models: A Comprehensive Surveyaccepted
ProtoVQA: An Adaptable Prototypical Framework for Explainable Fine-Grained Visual Question Answeringaccepted
ProtoXTM: Cross-Lingual Topic Modeling with Document-Level Prototype-based Contrastive Learningaccepted
Prototypical Human-AI Collaboration Behaviors from LLM-Assisted Writing in the Wildaccepted
Proxy Barrier: A Hidden Repeater Layer Defense Against System Prompt Leakage and Jailbreakingaccepted
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factualityaccepted
Pruning Weights but Not Truth: Safeguarding Truthfulness While Pruning LLMsaccepted
Pruning the Paradox: How CLIP’s Most Informative Heads Enhance Performance While Amplifying Biasaccepted
PsyScam: A Benchmark for Psychological Techniques in Real-World Scamsaccepted
Public Data Assisted Differentially Private In-Context Learningaccepted
Pun Unintended: LLMs and the Illusion of Humor Understandingaccepted
PunMemeCN: A Benchmark to Explore Vision-Language Models’ Understanding of Chinese Pun Memesaccepted
Puzzled by Puzzles: When Vision-Language Models Can’t Take a Hintaccepted
PychoAgent: Psychology-driven LLM Agents for Explainable Panic Prediction on Social Media during Sudden Disaster Eventsaccepted
Q-PRM: Adaptive Query Rewriting for Retrieval-Augmented Generation via Step-level Process Supervisionaccepted
QA‐LIGN: Aligning LLMs through Constitutionally Decomposed QAaccepted
QCRD: Quality-guided Contrastive Rationale Distillation for Large Language Modelsaccepted
QEVA: A Reference-Free Evaluation Metric for Narrative Video Summarization with Multimodal Question Answeringaccepted
QFrCoLA: a Quebec-French Corpus of Linguistic Acceptability Judgmentsaccepted
QG-CoC: Question-Guided Chain-of-Captions for Large Multimodal Modelsaccepted
QSpec: Speculative Decoding with Complementary Quantization Schemesaccepted
QUARTZ: QA-based Unsupervised Abstractive Refinement for Task-oriented Dialogue Summarizationaccepted
QUIDS: Query Intent Description for Exploratory Search via Dual Space Modelingaccepted
QUITO-X: A New Perspective on Context Compression from the Information Bottleneck Theoryaccepted
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Modelsaccepted
QualBench: Benchmarking Chinese LLMs with Localized Professional Qualifications for Vertical Domain Evaluationaccepted
QuantAgents: Towards Multi-agent Financial System via Simulated Tradingaccepted
Quantifying Compositionality of Classic and State-of-the-Art Embeddingsaccepted
Quantifying Language Disparities in Multilingual Large Language Modelsaccepted
Quantifying Logical Consistency in Transformers via Query-Key Alignmentaccepted
Quantifying Uncertainty in Natural Language Explanations of Large Language Models for Question Answeringaccepted
Quantifying the Risks of LLM- and Tool-assisted Rephrasing to Linguistic Diversityaccepted
Quantized but Deceptive? A Multi-Dimensional Truthfulness Evaluation of Quantized LLMsaccepted
Query Optimization for Parametric Knowledge Refinement in Retrieval-Augmented Large Language Modelsaccepted
Query-Focused Retrieval Heads Improve Long-Context Reasoning and Re-rankingaccepted
R-BPE: Improving BPE-Tokenizers with Token Reuseaccepted
R-Bind: Unified Enhancement of Attribute and Relation Binding in Text-to-Image Diffusion Modelsaccepted
R-CHAR: A Metacognition-Driven Framework for Role-Playing in Large Language Modelsaccepted
R-LoRA: Randomized Multi-Head LoRA for Efficient Multi-task Learningaccepted
R-PRM: Reasoning-Driven Process Reward Modelingaccepted
R-TOFU: Unlearning in Large Reasoning Modelsaccepted
R2A-TLS: Reflective Retrieval-Augmented Timeline Summarization with Causal-Semantic Integrationaccepted
R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generationaccepted
R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learningaccepted
RAC: Efficient LLM Factuality Correction with Retrieval Augmentationaccepted
RACCooN: Versatile Instructional Video Editing with Auto-Generated Narrativesaccepted
RACQC: Advanced Retrieval-Augmented Generation for Chinese Query Correctionaccepted
RAED: Retrieval-Augmented Entity Description Generation for Emerging Entity Linking and Disambiguationaccepted
RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware Reasoningaccepted
RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented Instructionsaccepted
RAG-Zeval: Enhancing RAG Responses Evaluator through End-to-End Reasoning and Ranking-Based Reinforcement Learningaccepted
RAGferee: Building Contextual Reward Models for Retrieval-Augmented Generationaccepted
RAISE: Reinforced Adaptive Instruction Selection For Large Language Modelsaccepted
RALS: Resources and Baselines for Romanian Automatic Lexical Simplificationaccepted
RAR2: Retrieval-Augmented Medical Reasoning via Thought-Driven Retrievalaccepted
RAV: Retrieval-Augmented Voting for Tactile Descriptions Without Trainingaccepted
RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Languageaccepted
RAcQUEt: Unveiling the Dangers of Overlooked Referential Ambiguity in Visual LLMsaccepted
RBPtool: A Deep Language Model Framework for Multi-Resolution RBP-RNA Binding Prediction and RNA Molecule Designaccepted
RCScore: Quantifying Response Consistency in Large Language Modelsaccepted
RD-MCSA: A Multi-Class Sentiment Analysis Approach Integrating In-Context Classification Rationales and Demonstrationsaccepted
REACT: Representation Extraction And Controllable Tuning to Overcome Overfitting in LLM Knowledge Editingaccepted
REALM: Recursive Relevance Modeling for LLM-based Document Re-Rankingaccepted
REAR: Reinforced Reasoning Optimization for Event Argument Extraction with Relation-Aware Supportaccepted
REARANK: Reasoning Re-ranking Agent via Reinforcement Learningaccepted
RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Mergingaccepted
RECAST: Retrieval-Augmented Contextual ASR via Decoder-State Keyword Spottingaccepted
RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward Redistributionaccepted
REGen: A Reliable Evaluation Framework for Generative Event Argument Extractionaccepted
RELIC: Enhancing Reward Model Generalization for Low-Resource Indic Languages with Few-Shot Examplesaccepted
RESF: Regularized-Entropy-Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Modelsaccepted
RETAIL: Towards Real-world Travel Planning for Large Language Modelsaccepted
REVIVING YOUR MNEME: Predicting The Side Effects of LLM Unlearning and Fine-Tuning via Sparse Model Diffingaccepted
RG-VQA: Leveraging Retriever-Generator Pipelines for Knowledge Intensive Visual Question Answeringaccepted
RGAR: Recurrence Generation-augmented Retrieval for Factual-aware Medical Question Answeringaccepted
RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstructionaccepted
RIVAL: Reinforcement Learning with Iterative and Adversarial Optimization for Machine Translationaccepted
RJE: A Retrieval-Judgment-Exploration Framework for Efficient Knowledge Graph Question Answering with LLMsaccepted
RLAE: Reinforcement Learning-Assisted Ensemble for LLMsaccepted
RLMEval: Evaluating Research-Level Neural Theorem Provingaccepted
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playingaccepted
ROSE: A Reward-Oriented Data Selection Framework for LLM Task-Specific Instruction Tuningaccepted
RPDR: A Round-trip Prediction-Based Data Augmentation Framework for Long-Tail Question Answeringaccepted
RRInf: Efficient Influence Function Estimation via Ridge Regression for Large Language Models and Text-to-Image Diffusion Modelsaccepted
RTE-GMoE: A Model-agnostic Approach for Relation Triplet Extraction via Graph-based Mixture-of-Expert Mutual Learningaccepted
RTQA : Recursive Thinking for Complex Temporal Knowledge Graph Question Answering with Large Language Modelsaccepted
RTTC: Reward-Guided Collaborative Test-Time Computeaccepted
RaDeR: Reasoning-aware Dense Retrieval Modelsaccepted
RadialRouter: Structured Representation for Efficient and Robust Large Language Models Routingaccepted
Radical Allomorphy: Phonological Surface Forms without Phonologyaccepted
Randomized Smoothing Meets Vision-Language Modelsaccepted
Randomly Removing 50% of Dimensions in Text Embeddings has Minimal Impact on Retrieval and Classification Tasksaccepted
Rank-Awareness and Angular Constraints: A New Perspective on Learning Sentence Embeddings from NLI Dataaccepted
Rapid Word Learning Through Meta In-Context Learningaccepted
RareSyn: Health Record Synthesis for Rare Disease Diagnosisaccepted
Rating Roulette: Self-Inconsistency in LLM-As-A-Judge Frameworksaccepted
Re-Align: Aligning Vision Language Models via Retrieval-Augmented Direct Preference Optimizationaccepted
Re-FRAME the Meeting Summarization SCOPE: Fact-Based Summarization and Personalization via Questionsaccepted
ReAL: How Can LLMs Simulate the Real Teacher? Retrieval-enhanced Agent for Adaptive Learningaccepted
ReAgent: Reversible Multi-Agent Reasoning for Knowledge-Enhanced Multi-Hop QAaccepted
ReAlign: Structured Revision for Small Language Model Alignmentaccepted
ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimizationaccepted
ReCoVeR the Target Language: Language Steering without Sacrificing Task Performanceaccepted
ReDepress: A Cognitive Framework for Detecting Depression Relapse from Social Mediaaccepted
ReEvalMed: Rethinking Medical Report Evaluation by Aligning Metrics with Real-World Clinical Judgmentaccepted
ReFLAIR: Enhancing Multimodal Reasoning via Structured Reflection and Reward-Guided Learningaccepted
ReGraphRAG: Reorganizing Fragmented Knowledge Graphs for Multi-Perspective Retrieval-Augmented Generationaccepted
ReLoop: “Seeing Twice and Thinking Backwards” via Closed-loop Training to Mitigate Hallucinations in Multimodal understandingaccepted
ReMamba: Equip Mamba with Effective Long-Sequence Modelingaccepted
ReMedy: Learning Machine Translation Evaluation from Human Preferences with Reward Modelingaccepted
ReSURE: Regularizing Supervision Unreliability for Multi-turn Dialogue Fine-tuningaccepted
ReSeeding Latent States for Sequential Language Understandingaccepted
ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasksaccepted
ReTAG: Retrieval-Enhanced, Topic-Augmented Graph-Based Global Sensemakingaccepted
Read to Hear: A Zero-Shot Pronunciation Assessment Using Textual Descriptions and LLMsaccepted
Reading Between the Prompts: How Stereotypes Shape LLM’s Implicit Personalizationaccepted
Real, Fake, or Manipulated? Detecting Machine-Influenced Textaccepted
Real-World Summarization: When Evaluation Reaches Its Limitsaccepted
Real-time Ad Retrieval via LLM-generative Commercial Intention for Sponsored Search Advertisingaccepted
RealBench: A Chinese Multi-image Understanding Benchmark Close to Real-world Scenariosaccepted
Realistic Training Data Generation and Rule Enhanced Decoding in LLM for NameGuessaccepted
Reason to Rote: Rethinking Memorization in Reasoningaccepted
ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoningaccepted
Reasoning Model Unlearning: Forgetting Traces, Not Just Answers, While Preserving Reasoning Skillsaccepted
Reasoning under Uncertainty: Efficient LLM Inference via Unsupervised Confidence Dilution and Convergent Adaptive Samplingaccepted
Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Modelsaccepted
Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreakingaccepted
RecBase: Generative Foundation Model Pretraining for Zero-Shot Recommendationaccepted
RecGPT: A Foundation Model for Sequential Recommendationaccepted
Recall with Reasoning: Chain-of-Thought Distillation for Mamba’s Long-Context Memory and Extrapolationaccepted
Recipe2Plan: Evaluating Planning Abilities of LLMs for Efficient and Feasible Multitasking with Time Constraints Between Actionsaccepted
Recognizing Limits: Investigating Infeasibility in Large Language Modelsaccepted
Recontextualizing Revitalization: A Mixed Media Approach to Reviving the Nüshu Languageaccepted
Recursive Training Loops in LLMs: How training data properties modulate distribution shift in generated data?accepted
RedHerring Attack: Testing the Reliability of Attack Detectionaccepted
RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generationaccepted
Refined Assessment for Translation Evaluation: Rethinking Machine Translation Evaluation in the Era of Human-Level Systemsaccepted
Refining Attention for Explainable and Noise-Robust Fact-Checking with Transformersaccepted
Refining Text Generation for Realistic Conversational Recommendation via Direct Preference Optimizationaccepted
ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflectionaccepted
Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extractionaccepted
Reframe Your Life Story: Interactive Narrative Therapist and Innovative Moment Assessment with Large Language Modelsaccepted
Refusal-Aware Red Teaming: Exposing Inconsistency in Safety Evaluationsaccepted
Regularized Contrastive Decoding with Hard Negative Samples for LLM Hallucination Mitigationaccepted
Reimagining Safety Alignment with An Imageaccepted
Reinforced Query Reasoners for Reasoning-intensive Retrieval Tasksaccepted
Reinforcement Learning for Large Language Models via Group Preference Reward Shapingaccepted
Reinforcement Learning with Supervised Alignmentaccepted
Reliability Crisis of Reference-free Metrics for Grammatical Error Correctionaccepted
Reliable Evaluation and Benchmarks for Statement Autoformalizationaccepted
Reliable and Cost-Effective Exploratory Data Analysis via Graph-Guided RAGaccepted
ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Momentsaccepted
RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Modelsaccepted
Representation Potentials of Foundation Models for Multimodal Alignment: A Surveyaccepted
Representation-based Broad Hallucination Detectors Fail to Generalize Out of Distributionaccepted
Representing LLMs in Prompt Semantic Task Spaceaccepted
ResFormer: All-Time Reservoir Memory for Long Sequence Classificationaccepted
Rescorla-Wagner Steering of LLMs for Undesired Behaviors over Disproportionate Inappropriate Contextaccepted
ResearchArena: Benchmarking Large Language Models’ Ability to Collect and Organize Information as Research Agentsaccepted
Reshaping Representation Space to Balance the Safety and Over-rejection in Large Audio Language Modelsaccepted
Residualized Similarity for Faithfully Explainable Authorship Verificationaccepted
Resolving UnderEdit & OverEdit with Iterative & Neighbor-Assisted Model Editingaccepted
Resource-Rational Noisy-Channel Language Processing: Testing the Effect of Algorithmic Constraints on Inferencesaccepted
Rethink Rumor Detection in the Era of LLMs: A Reviewaccepted
RethinkMCTS: Refining Erroneous Thoughts in Monte Carlo Tree Search for Code Generationaccepted
Rethinking Backdoor Detection Evaluation for Language Modelsaccepted
Rethinking Cross-Subject Data Splitting for Brain-to-Text Decodingaccepted
Rethinking DPO: The Role of Rejected Responses in Preference Misalignmentaccepted
Rethinking Data Selection at Scale: Random Selection is Almost All You Needaccepted
Rethinking LLM Uncertainty: A Multi-Agent Approach to Estimating Black-Box Model Uncertaintyaccepted
Rethinking LLM-Based Recommendations: A Personalized Query-Driven Parallel Integrationaccepted
Rethinking NLP for Chemistry: A Critical Look at the USPTO Benchmarkaccepted
Rethinking Personality Assessment from Human-Agent Dialogues: Fewer Rounds May Be Better Than Moreaccepted
Rethinking Sign Language Translation: The Impact of Signer Dependence on Model Evaluationaccepted
Rethinking Text-based Protein Understanding: Retrieval or LLM?accepted
Retracing the Past: LLMs Emit Training Data When They Get Lostaccepted
Retrieval Augmented Generation based context discovery for ASRaccepted
Retrieval Enhanced Feedback via In-context Neural Error-bookaccepted
Retrieval over Classification: Integrating Relation Semantics for Multimodal Relation Extractionaccepted
Retrieval-Augmented Generation with Estimation of Source Reliabilityaccepted
Retrieval-Augmented Generation with Hierarchical Knowledgeaccepted
Retrieval-Augmented Language Models are Mimetic Theorem Proversaccepted
Retrieval-Augmented Machine Translation with Unstructured Knowledgeaccepted
Retrieval-augmented GUI Agents with Generative Guidelinesaccepted
Retrieving Support to Rank Answers in Open-Domain Question Answeringaccepted
RevPRAG: Revealing Poisoning Attacks in Retrieval-Augmented Generation through LLM Activation Analysisaccepted
Reveal and Release: Iterative LLM Unlearning with Self-generated Dataaccepted
Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-Playingaccepted
Revealing the Inherent Instructability of Pre-Trained Language Modelsaccepted
Revealing the impact of synthetic native samples and multi-tasking strategies in Hindi-English code-mixed humour and sarcasm detectionaccepted
Reverse Prompt Engineering: A Zero-Shot, Genetic Algorithm Approach to Language Model Inversionaccepted
ReviewEval: An Evaluation Framework for AI-Generated Reviewsaccepted
ReviewRL: Towards Automated Scientific Review with RLaccepted
Revisiting Chain-of-Thought Prompting: Zero-shot Can Be Stronger than Few-shotaccepted
Revisiting LLM Value Probing Strategies: Are They Robust and Expressive?accepted
Revisiting Pruning vs Quantization for Small Language Modelsaccepted
Reward Mixology: Crafting Hybrid Signals for Reinforcement Learning Driven In-Context Learningaccepted
Reward Model Perspectives: Whose Opinions Do Reward Models Reward?accepted
Reward-Shifted Speculative Sampling Is An Efficient Test-Time Weak-to-Strong Aligneraccepted
Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMsaccepted
RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesisaccepted
Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpeningaccepted
RiTTA: Modeling Event Relations in Text-to-Audio Generationaccepted
Riemannian Optimization for LoRA on the Stiefel Manifoldaccepted
RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signalsaccepted
RoDEval: A Robust Word Sense Disambiguation Evaluation Framework for Large Language Modelsaccepted
RoT: Enhancing Table Reasoning with Iterative Row-Wise Traversalsaccepted
Robust Adaptation of Large Multimodal Models for Retrieval Augmented Hateful Meme Detectionaccepted
Robust Knowledge Editing via Explicit Reasoning Chains for Distractor-Resilient Multi-Hop QAaccepted
Robust Native Language Identification through Agentic Decompositionaccepted
Role-Guided Annotation and Prototype-Aligned Representation Learning for Historical Literature Sentiment Classificationaccepted
Rotate, Clip, and Partition: Towards W2A4KV4 Quantization by Integrating Rotation and Learnable Non-uniform Quantizeraccepted
Route Sparse Autoencoder to Interpret Large Language Modelsaccepted
Router-Tuning: A Simple and Effective Approach for Dynamic Depthaccepted
RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMsaccepted
RuCCoD: Towards Automated ICD Coding in Russianaccepted
Rule Discovery for Natural Language Inference Data Generation Using Out-of-Distribution Detectionaccepted
Rule-Guided Extraction: A Hierarchical Rule Optimization Framework for Document-Level Event Argument Extractionaccepted
Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environmentsaccepted
Rust-doctor: Enhanced Feature for Rust Ownership and Lifetime Repair with Balanced Training Data Generationaccepted
S*: Test Time Scaling for Code Generationaccepted
S2LPP: Small-to-Large Prompt Prediction across LLMsaccepted
SA-CLIP: Language Guided Image Spatial and Action Feature Learningaccepted
SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connectionaccepted
SACL: Understanding and Combating Textual Bias in Code Retrieval with Semantic-Augmented Reranking and Localizationaccepted
SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Modelsaccepted
SAEs Are Good for Steering – If You Select the Right Featuresaccepted
SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQLaccepted
SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMsaccepted
SAFE: Schema-Driven Approximate Distance Join for Efficient Knowledge Graph Queryingaccepted
SAFENUDGE: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offsaccepted
SAKI-RAG: Mitigating Context Fragmentation in Long-Document RAG via Sentence-level Attention Knowledge Integrationaccepted
SAMULE: Self-Learning Agents Enhanced by Multi-level Reflectionaccepted
SAND: Boosting LLM Agents with Self-Taught Action Deliberationaccepted
SATBench: Benchmarking LLMs’ Logical Reasoning via Automated Puzzle Generation from SAT Formulasaccepted
SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascadingaccepted
SCDTour: Embedding Axis Ordering and Merging for Interpretable Semantic Change Detectionaccepted
SCE: Semantic Consistency Enhanced Reinforcement Learning for Multi-Hop Knowledge Graph Reasoningaccepted
SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Callingaccepted
SCoder: Progressive Self-Distillation for Bootstrapping Small-Scale Data Synthesizers to Empower Code LLMsaccepted
SDGO: Self-Discrimination-Guided Optimization for Consistent Safety in Large Language Modelsaccepted
SEA: Supervised Embedding Alignment for Token-Level Visual-Textual Integration in MLLMsaccepted
SEAL: Structure and Element Aware Learning Improves Long Structured Document Retrievalaccepted
SEKE: Specialised Experts for Keyword Extractionaccepted
SEMMA: A Semantic Aware Knowledge Graph Foundation Modelaccepted
SENTRA: Selected-Next-Token Transformer for LLM Text Detectionaccepted
SEPS: A Separability Measure for Robust Unlearning in LLMsaccepted
SERVAL: Surprisingly Effective Zero-Shot Visual Document Retrieval Powered by Large Vision and Language Modelsaccepted
SGCD: Subtask-Guided Causal-Debiasing Framework for Robust Cross-Utterance Sentiment Quadruple Extraction in Dialoguesaccepted
SHARP: Steering Hallucination in LVLMs via Representation Engineeringaccepted
SHIFT: Selected Helpful Informative Frame for Video-guided Machine Translationaccepted
SIFT: Grounding LLM Reasoning in Contexts via Stickersaccepted
SIMBA UQ: Similarity-Based Aggregation for Uncertainty Quantification in Large Language Modelsaccepted
SKA-Bench: A Fine-Grained Benchmark for Evaluating Structured Knowledge Understanding of LLMsaccepted
SKRAG: A Retrieval-Augmented Generation Framework Guided by Reasoning Skeletons over Knowledge Graphsaccepted
SLIM: Subtrajectory-Level Elimination for More Effective Reasoningaccepted
SLM-Bench: A Comprehensive Benchmark of Small Language Models on Environmental Impactsaccepted
SLiNT: Structure-aware Language Model with Injection and Contrastive Training for Knowledge Graph Completionaccepted
SLlama: Parameter-Efficient Language Model Architecture for Enhanced Linguistic Competence Under Strict Data Constraintsaccepted
SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Modelsaccepted
SMART: Simulated Students Aligned with Item Response Theory for Question Difficulty Predictionaccepted
SMARTMiner: Extracting and Evaluating SMART Goals from Low-Resource Health Coaching Notesaccepted
SMEC:Rethinking Matryoshka Representation Learning for Retrieval Embedding Compressionaccepted
SNaRe: Domain-aware Data Generation for Low-Resource Event Detectionaccepted
SOCIAL SCAFFOLDS: A Generalization Framework for Social Understanding Tasksaccepted
SOLAR: Serendipity Optimized Language Model Aligned for Recommendationaccepted
SOLAR: Towards Characterizing Subjectivity of Individuals through Modeling Value Conflicts and Trade-offsaccepted
SOPL: A Sequential Optimal Learning Approach to Automated Prompt Engineering in Large Language Modelsaccepted
SPARK: Simulating the Co-evolution of Stance and Topic Dynamics in Online Discourse with LLM-based Agentsaccepted
SPE Attention: Making Attention Equivariant to Semantic-Preserving Permutation for Code Processingaccepted
SPECS: Specificity-Enhanced CLIP-Score for Long Image Caption Evaluationaccepted
SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuningaccepted
SPIRIT: Patching Speech Language Models against Jailbreak Attacksaccepted
SPO: Self Preference Optimization with Self Regularizationaccepted
SPPD: Self-training with Process Preference Learning Using Dynamic Value Marginaccepted
SPaRC: A Spatial Pathfinding Reasoning Challengeaccepted
SQLSpace: A Representation Space for Text-to-SQL to Discover and Mitigate Robustness Gapsaccepted
SQLWOZ: A Realistic Task-Oriented Dialogue Dataset with SQL-Based Dialogue State Representation for Complex User Requirementsaccepted
SQUAB: Evaluating LLM robustness to Ambiguous and Unanswerable Questions in Semantic Parsingaccepted
SQUARE: Unsupervised Retrieval Adaptation via Synthetic Dataaccepted
SQUiD: Synthesizing Relational Databases from Unstructured Textaccepted
SRM-LLM: Semantic Relationship Mining with LLMs for Temporal Knowledge Graph Extrapolationaccepted
SSA-COMET: Do LLMs Outperform Learned Metrics in Evaluating MT for Under-Resourced African Languages?accepted
SSA: Semantic Contamination of LLM-Driven Fake News Detectionaccepted
STA-CoT: Structured Target-Centric Agentic Chain-of-Thought for Consistent Multi-Image Geological Reasoningaccepted
STARE at the Structure: Steering ICL Exemplar Selection with Structural Alignmentaccepted
STARQA: A Question Answering Dataset for Complex Analytical Reasoning over Structured Databasesaccepted
START: Self-taught Reasoner with Toolsaccepted
STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Modelsaccepted
STEER-BENCH: A Benchmark for Evaluating the Steerability of Large Language Modelsaccepted
STRICT: Stress-Test of Rendering Image Containing Textaccepted
SUA: Stealthy Multimodal Large Language Model Unlearning Attackaccepted
SUE: Sparsity-based Uncertainty Estimation via Sparse Dictionary Learningaccepted
SURE: Safety Understanding and Reasoning Enhancement for Multimodal Large Language Modelsaccepted
SVeritas: Benchmark for Robust Speaker Verification under Diverse Conditionsaccepted
SWAM: Adaptive Sliding Window and Memory-Augmented Attention Model for Rumor Detectionaccepted
SWAN: An Efficient and Scalable Approach for Long-Context Language Modelingaccepted
SYNC: A Synthetic Long-Context Understanding Benchmark for Controlled Comparisons of Model Capabilitiesaccepted
SaCa: A Highly Compatible Reinforcing Framework for Knowledge Graph Embedding via Structural Pattern Contrastaccepted
SafeConf: A Confidence-Calibrated Safety Self-Evaluation Method for Large Language Modelsaccepted
SafeInt: Shielding Large Language Models from Jailbreak Attacks via Safety-Aware Representation Interventionaccepted
SafeKey: Amplifying Aha-Moment Insights for Safety Reasoningaccepted
SafeScientist: Enhancing AI Scientist Safety for Risk-Aware Scientific Discoveryaccepted
SafeSwitch: Steering Unsafe LLM Behavior via Internal Activation Signalsaccepted
SafeToolBench: Pioneering a Prospective Benchmark to Evaluating Tool Utilization Safety in LLMsaccepted
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Mergingaccepted
Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?accepted
Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Modelsaccepted
Safety in Large Reasoning Models: A Surveyaccepted
SalaMAnder: Shapley-based Mathematical Expression Attribution and Metric for Chain-of-Thought Reasoningaccepted
Sali4Vid: Saliency-Aware Video Reweighting and Adaptive Caption Retrieval for Dense Video Captioningaccepted
Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustnessaccepted
Same evaluation, more tokens: On the effect of input length for machine translation evaluation using Large Language Modelsaccepted
Sample Efficient Alignment Learning With Episodic Controlaccepted
SampleMix: A Sample-wise Pre-training Data Mixing Strategy by Coordinating Data Quality and Diversityaccepted
Sarcasm-R1: Enhancing Sarcasm Detection through Focused Reasoningaccepted
Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Modelsaccepted
Scalable Data Synthesis through Human-like Cognitive Imitation and Data Recombinationaccepted
Scalable and Culturally Specific Stereotype Dataset Construction via Human-LLM Collaborationaccepted
Scale Down to Speed Up: Dynamic Data Selection for Reinforcement Learningaccepted
Scaling Laws Are Unreliable for Downstream Tasks: A Reality Checkaccepted
Scaling Low-Resource MT via Synthetic Data Generation with LLMsaccepted
Scaling Rich Style-Prompted Text-to-Speech Datasetsaccepted
Scaling Up Temporal Domain Generalization via Temporal Experts Averagingaccepted
Schema Generation for Large Knowledge Graphs Using Large Language Modelsaccepted
ScholarBench: A Bilingual Benchmark for Abstraction, Comprehension, and Reasoning Evaluation in Academic Contextsaccepted
SciCompanion: Graph-Grounded Reasoning for Structured Evaluation of Scientific Argumentsaccepted
SciEvent: Benchmarking Multi-domain Scientific Event Extractionaccepted
SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLPaccepted
SciRIFF: A Resource to Enhance Language Model Instruction-Following over Scientific Literatureaccepted
Scientific Paper Retrieval with LLM-Guided Semantic-Based Rankingaccepted
SeMob: Semantic Synthesis for Dynamic Urban Mobility Predictionaccepted
SeaPO: Strategic Error Amplification for Robust Preference Optimization of Large Language Modelsaccepted
Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertaintyaccepted
Search-o1: Agentic Search-Enhanced Large Reasoning Modelsaccepted
Searching for the Most Human-like Emergent Languageaccepted
SecDecoding: Steerable Decoding for Safer LLM Generationaccepted
Section-Level Simplification of Biomedical Abstractsaccepted
Seeing Culture: A Benchmark for Visual Reasoning and Groundingaccepted
Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressorsaccepted
Seeing Race, Feeling Bias: Emotion Stereotyping in Multimodal Language Modelsaccepted
Seeing Through Words, Speaking Through Pixels: Deep Representational Alignment Between Vision and Language Modelsaccepted
Seeing is Believing, but How Much? A Comprehensive Analysis of Verbalized Calibration in Vision-Language Modelsaccepted
Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generationaccepted
Seeing the Same Story Differently: Framing‐Divergent Event Coreference for Computational Framing Analysisaccepted
Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answeringaccepted
Select-Then-Decompose: From Empirical Analysis to Adaptive Selection Strategy for Task Decomposition in Large Language Modelsaccepted
Selective Preference Optimization via Token-Level Reward Function Estimationaccepted
Self-Adjust Softmaxaccepted
Self-Augmented Preference Alignment for Sycophancy Reduction in LLMsaccepted
Self-Correcting Code Generation Using Small Language Modelsaccepted
Self-Correction Makes LLMs Better Parsersaccepted
Self-Critique and Refinement for Faithful Natural Language Explanationsaccepted
Self-Ensemble: Mitigating Confidence Distortion for Large Language Modelsaccepted
Self-Guided Function Calling in Large Language Models via Stepwise Experience Recallaccepted
Self-Improvement in Multimodal Large Language Models: A Surveyaccepted
Self-Supervised Prompt Optimizationaccepted
Self-Training Large Language Models with Confident Reasoningaccepted
Self-adaptive Dataset Construction for Real-World Multimodal Safety Scenariosaccepted
SelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignmentaccepted
SelfRACG: Enabling LLMs to Self-Express and Retrieve for Code Generationaccepted
SemCSE: Semantic Contrastive Sentence Embeddings Using LLM-Generated Summaries For Scientific Abstractsaccepted
SemVink: Advancing VLMs’ Semantic Understanding of Optical Illusions via Visual Global Thinkingaccepted
Semantic Component Analysis: Introducing Multi-Topic Distributions to Clustering-Based Topic Modelingaccepted
Semantic Contribution-Aware Adaptive Retrieval for Black-Box Modelsaccepted
Semantic Geometry of Sentence Embeddingsaccepted
Semantic Inversion, Identical Replies: Revisiting Negation Blindness in Large Language Modelsaccepted
Semantic Networks Extracted from Students’ Think-Aloud Data are Correlated with Students’ Learning Performanceaccepted
Semantic-Aware Action Space Compression via LLM-DRL Synergy for Efficient Task-oriented Dialogue Policy Explorationaccepted
SenDetEX: Sentence-Level AI-Generated Text Detection for Human-AI Hybrid Content via Style and Context Fusionaccepted
Sensitivity-LoRA : Low-Load Sensitivity-Based Fine-Tuning for Large Language Modelsaccepted
SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognitionaccepted
Sentence Smith: Controllable Edits for Evaluating Text Embeddingsaccepted
Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generationaccepted
Sequence Structure Aware Retriever for Procedural Document Retrieval: A New Dataset and Baselineaccepted
Sequential-NIAH: A Needle-In-A-Haystack Benchmark for Extracting Sequential Needles from Long Contextsaccepted
Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLMsaccepted
Shared Path: Unraveling Memorization in Multilingual LLMs through Language Similaritiesaccepted
Sheaf Discovery with Joint Computation Graph Pruning and Flexible Granularityaccepted
SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflectionaccepted
Should I Share this Translation? Evaluating Quality Feedback for User Reliance on Machine Translationaccepted
Side Effects of Erasing Concepts from Diffusion Modelsaccepted
SilVar: Speech-Driven Multimodal Model for Reasoning Visual Question Answering and Object Localizationaccepted
SimBA: Simplifying Benchmark Analysis Using Performance Matrices Aloneaccepted
SimMark: A Robust Sentence-Level Similarity-Based Watermarking Algorithm for Large Language Modelsaccepted
SimVBG: Simulating Individual Values by Backstory Generationaccepted
Similarity = Value? Consultation Value-Assessment and Alignment for Personalized Searchaccepted
Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generationaccepted
Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantificationaccepted
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesisaccepted
SimpleDoc: Multi‐Modal Document Understanding with Dual‐Cue Page Retrieval and Iterative Refinementaccepted
Simulating Identity, Propagating Bias: Abstraction and Stereotypes in LLM-Generated Textaccepted
SimulatorArena: Are User Simulators Reliable Proxies for Multi-Turn Evaluation of AI Assistants?accepted
Single LLM, Multiple Roles: A Unified Retrieval-Augmented Generation Framework Using Role-Specific Token Optimizationaccepted
SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhalaaccepted
Skeleton-Guided-Translation: A Benchmarking Framework for Code Repository Translation with Fine-Grained Quality Evaluationaccepted
Skeletons Matter: Dynamic Data Augmentation for Text-to-Queryaccepted
Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketchingaccepted
SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Contextaccepted
Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Fasteraccepted
SliceMoE: Routing Embedding Slices Instead of Tokens for Fine-Grained and Balanced Transformer Scalingaccepted
SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Designaccepted
Slim-SC: Thought Pruning for Efficient Scaling with Self-Consistencyaccepted
Small Models, Big Results: Achieving Superior Intent Extraction through Decompositionaccepted
Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learningaccepted
SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?accepted
SoT: Structured-of-Thought Prompting Guides Multilingual Reasoning in Large Language Modelsaccepted
Social Bias Evaluation for Large Language Models Requires Prompt Variationsaccepted
Social Bias in Multilingual Language Models: A Surveyaccepted
Social Genome: Grounded Social Reasoning Abilities of Multimodal Modelsaccepted
Social Good or Scientific Curiosity? Uncovering the Research Framing Behind NLP Artefactsaccepted
SocioBench: Modeling Human Behavior in Sociological Surveys with Large Language Modelsaccepted
Socratic-MCTS: Test-Time Visual Reasoning by Asking the Right Questionsaccepted
Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Modelsaccepted
SolEval: Benchmarking Large Language Models for Repository-level Solidity Smart Contract Generationaccepted
Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignmentaccepted
SoundMind: RL-Incentivized Logic Reasoning for Audio-Language Modelsaccepted
Source-primed Multi-turn Conversation Helps Large Language Models Translate Documentsaccepted
Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Spatial Reasoningaccepted
Sparse Activation Editing for Reliable Instruction Following in Narrativesaccepted
Sparse Autoencoder Features for Classifications and Transferabilityaccepted
Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMsaccepted
SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masksaccepted
Sparsifying Mambaaccepted
Sparsity May Be All You Need: Sparse Random Parameter Adaptationaccepted
Spatial Layouts in News Homepages Capture Human Preferencesaccepted
Speaking at the Right Level: Literacy-Controlled Counterspeech Generation with RAG-RLaccepted
Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptanceaccepted
SpecCoT: Accelerating Chain-of-Thought Reasoning through Speculative Explorationaccepted
SpecVLM: Enhancing Speculative Decoding of Video LLMs via Verifier-Guided Token Pruningaccepted
Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space?accepted
Speculating LLMs’ Chinese Training Data Pollution from Their Tokensaccepted
Speculative Decoding for Multi-Sample Inferenceaccepted
Speculative Safety-Aware Decodingaccepted
Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attentionaccepted
Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMsaccepted
Speech Vecalign: an Embedding-based Method for Aligning Parallel Speech Documentsaccepted
Spelling-out is not Straightforward: LLMs’ Capability of Tokenization from Token to Charactersaccepted
Spiral of Silence in Large Language Model Agentsaccepted
Split-Merge: Scalable and Memory-Efficient Merging of Expert LLMsaccepted
Spoken Document Retrieval for an Unwritten Language: A Case Study on Gormatiaccepted
Spontaneous Giving and Calculated Greed in Language Modelsaccepted
SportReason: Evaluating Retrieval-Augmented Reasoning across Tables and Text for Sports Question Answeringaccepted
Spotlighter: Revisiting Prompt Tuning from a Representative Mining Viewaccepted
Staged Knowledge Distillation Through Least-to-Most Prompting: Optimizing Teacher Guidance via Difficulty-Aware Trainingaccepted
Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experienceaccepted
StandUp4AI: A New Multilingual Dataset for Humor Detection in Stand-up Comedy Videosaccepted
Static Word Embeddings for Sentence Semantic Representationaccepted
Static or Dynamic: Towards Query-Adaptive Token Selection for Video Question Answeringaccepted
Statistical and Neural Methods for Hawaiian Orthography Modernizationaccepted
StatsChartMWP: A Dataset for Evaluating Multimodal Mathematical Reasoning Abilities on Math Word Problems with Statistical Chartsaccepted
SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Modelsaccepted
Steering LLM Reasoning Through Bias-Only Adaptationaccepted
Steering LVLMs via Sparse Autoencoder for Hallucination Mitigationaccepted
Steering Language Models in Multi-Token Generation: A Case Study on Tense and Aspectaccepted
Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoningaccepted
Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Modelsaccepted
StepER: Step-wise Knowledge Distillation for Enhancing Reasoning Ability in Multi-Step Retrieval-Augmented Language Modelsaccepted
StepKE: Stepwise Knowledge Editing for Multi-Hop Question Answeringaccepted
StepSearch: Igniting LLMs Search Ability via Step-Wise Proximal Policy Optimizationaccepted
Stepwise Informativeness Search for Improving LLM Reasoningaccepted
Stepwise Reasoning Checkpoint Analysis: A Test Time Scaling Method to Enhance LLMs’ Reasoningaccepted
StereoDetect: Detecting Stereotypes and Anti-stereotypes the Correct Way Using Social Psychological Underpinningsaccepted
Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Frameworkaccepted
Stimulate the Critical Thinking of LLMs via Debiasing Discussionaccepted
Stop Looking for “Important Tokens” in Multimodal Language Models: Duplication Matters Moreaccepted
Stop Playing the Guessing Game! Evaluating Conversational Recommender Systems via Target-free User Simulationaccepted
Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategyaccepted
Stress-Testing the Reasoning Competence of Language Models With Formal Proofsaccepted
Stronger Baselines for Retrieval-Augmented Generation with Long-Context Language Modelsaccepted
StructuThink: Reasoning with Task Transition Knowledge for Autonomous LLM-Based Agentsaccepted
Structural Patent Classification Using Label Hierarchy Optimizationaccepted
Structure Trumps Size: Rethinking Data Quality for LLM Reasoningaccepted
Structure-Conditional Minimum Bayes Risk Decodingaccepted
Structure-aware Propagation Generation with Large Language Models for Fake News Detectionaccepted
Structured Moral Reasoning in Language Models: A Value-Grounded Evaluation Frameworkaccepted
Structured Preference Optimization for Vision-Language Long-Horizon Task Planningaccepted
Structuring Radiology Reports: Challenging LLMs with Lightweight Modelsaccepted
Studying Rhetorically Ambiguous Questionsaccepted
Studying the Role of Input-Neighbor Overlap in Retrieval-Augmented Language Models Training Efficiencyaccepted
SuPreME: A Supervised Pre-training Framework for Multimodal ECG Representation Learningaccepted
SubDocTrans: Enhancing Document-level Machine Translation with Plug-and-play Multi-granularity Knowledge Augmentationaccepted
Subjective Behaviors and Preferences in LLM: Language of Browsingaccepted
Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Makingaccepted
Sugar-Coated Poison: Benign Generation Unlocks Jailbreakingaccepted
Summarize-Exemplify-Reflect: Data-driven Insight Distillation Empowers LLMs for Few-shot Tabular Classificationaccepted
Summarizing Speech: A Comprehensive Surveyaccepted
Superficial Self-Improved Reasoners Benefit from Model Mergingaccepted
Superpose Task-specific Features for Model Mergingaccepted
Supervised Attention Mechanism for Low-quality Multimodal Dataaccepted
Surge: On the Potential of Large Language Models as General-Purpose Surrogate Code Executorsaccepted
Surprise Calibration for Better In-Context Learningaccepted
SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Modelsaccepted
SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligenceaccepted
SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformationaccepted
SwiftPrune: Hessian-Free Weight Pruning for Large Language Modelsaccepted
Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectoriesaccepted
SynC-LLM: Generation of Large-Scale Synthetic Circuit Code with Hierarchical Language Modelsaccepted
Synergizing Multimodal Temporal Knowledge Graphs and Large Language Models for Social Relation Recognitionaccepted
Syntax-Aware Retrieval Augmentation for Neural Symbolic Regressionaccepted
Synth-SBDH: A Synthetic Dataset of Social and Behavioral Determinants of Health for Clinical Textaccepted
Synthetic Socratic Debates: Examining Persona Effects on Moral Decision and Persuasion Dynamicsaccepted
T-MAD: Target-driven Multimodal Alignment for Stance Detectionaccepted
T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answeringaccepted
T2R-BENCH: A Benchmark for Real World Table-to-Report Taskaccepted
TABARD: A Novel Benchmark for Tabular Anomaly Analysis, Reasoning and Detectionaccepted
TACO: Enhancing Multimodal In-context Learning via Task Mapping-Guided Sequence Configurationaccepted
TALON: A Multi-Agent Framework for Long-Table Exploration and Question Answeringaccepted
TAPS: Tool-Augmented Personalisation via Structured Taggingaccepted
TASO: Task-Aligned Sparse Optimization for Parameter-Efficient Model Adaptationaccepted
TCP: a Benchmark for Temporal Constraint-Based Planningaccepted
TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-makingaccepted
TF-Mamba: Text-enhanced Fusion Mamba with Missing Modalities for Robust Multimodal Sentiment Analysisaccepted
TFDP: Token-Efficient Disparity Audits for Autoregressive LLMs via Single-Token Masked Evaluationaccepted
THCM-CAL: Temporal-Hierarchical Causal Modelling with Conformal Calibration for Clinical Risk Predictionaccepted
TIDES: Technical Information Discovery and Extraction Systemaccepted
TIU-Bench: A Benchmark for Evaluating Large Multimodal Models on Text-rich Image Understandingaccepted
TL-Training: A Task-Feature-Based Framework for Training Large Language Models in Tool Useaccepted
TLUE: A Tibetan Language Understanding Evaluation Benchmarkaccepted
TORSO: Template-Oriented Reasoning Towards General Tasksaccepted
TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planningaccepted
TR-MTEB: A Comprehensive Benchmark and Embedding Model Suite for Turkish Sentence Representationsaccepted
TRIAL: Token Relations and Importance Aware Late-interaction for Accurate Text Retrievalaccepted
TRUEBench: Can LLM Response Meet Real-world Constraints as Productivity Assistant?accepted
TRUST-VL: An Explainable News Assistant for General Multimodal Misinformation Detectionaccepted
TS-CLIP: Time Series Understanding by CLIPaccepted
TSVer: A Benchmark for Fact Verification Against Time-Series Evidenceaccepted
TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluationaccepted
TTT-Bench: A Benchmark for Evaluating Reasoning Ability with Simple and Novel Tic-Tac-Toe-style Gamesaccepted
TVQACML: Benchmarking Text-Centric Visual Question Answering in Multilingual Chinese Minority Languagesaccepted
TabDSR: Decompose, Sanitize, and Reason for Complex Numerical Reasoning in Tabular Dataaccepted
Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Fine-tuningaccepted
Table-R1: Inference-Time Scaling for Table Reasoning Tasksaccepted
Table-Text Alignment: Explaining Claim Verification Against Tables in Scientific Papersaccepted
TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answeringaccepted
TableRAG: A Retrieval Augmented Generation Framework for Heterogeneous Document Reasoningaccepted
TactfulToM: Do LLMs have the Theory of Mind ability to understand White Lies?accepted
Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attackaccepted
TailorRPA: A Retrieval-Based Framework for Eliciting Personalized and Coherent Role-Playing Agents in General Domainaccepted
Tailoring Table Retrieval from a Field-aware Hybrid Matching Perspectiveaccepted
Taking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learningaccepted
Tales of Morality: Comparing Human- and LLM-Generated Moral Stories from Visual Cuesaccepted
Taming Text-to-Image Synthesis for Novices: User-centric Prompt Generation via Multi-turn Guidanceaccepted
Targeted Distillation for Sentiment Analysisaccepted
Task-Aware Resolution Optimization for Visual Large Language Modelsaccepted
Task-aware Contrastive Mixture of Experts for Quadruple Extraction in Conversations with Code-like Replies and Non-opinion Detectionaccepted
TaxoAlign: Scholarly Taxonomy Generation Using Language Modelsaccepted
Teach Small Models to Reason by Curriculum Distillationaccepted
Teaching According to Talents! Instruction Tuning LLMs with Competence-Aware Curriculum Learningaccepted
Teaching LLMs to Plan, Not Just Solve: Plan Learning Boosts LLMs Generalization in Reasoning Tasksaccepted
Teaching Language Models To Gather Information Proactivelyaccepted
Teaching Your Models to Understand Code via Focal Preference Alignmentaccepted
TempParaphraser: “Heating Up” Text to Evade AI-Text Detection through Paraphrasingaccepted
Temporal Alignment of Time Sensitive Facts with Activation Engineeringaccepted
Temporal Consistency for LLM Reasoning Process Error Identificationaccepted
Temporal Referential Consistency: Do LLMs Favor Sequences Over Absolute Time References?accepted
Temporal Scaling Law for Large Language Modelsaccepted
Test-Time Steering for Lossless Text Compression via Weighted Product of Expertsaccepted
Text Anomaly Detection with Simplified Isolation Kernelaccepted
Text Detoxification: Data Efficiency, Semantic Preservation and Model Generalizationaccepted
Text Meets Topology: Rethinking Out-of-distribution Detection in Text-Rich Networksaccepted
Text Takes Over: A Study of Modality Bias in Multimodal Intent Detectionaccepted
Text or Pixels? Evaluating Efficiency and Understanding of LLMs with Visual Text Inputsaccepted
Text-centric Alignment for Bridging Test-time Unseen Modalityaccepted
Text2Vis: A Challenging and Diverse Benchmark for Generating Multimodal Visualizations from Textaccepted
Textual Aesthetics in Large Language Modelsaccepted
The Arabic Generality Score: Another Dimension of Modeling Arabic Dialectnessaccepted
The Effect of Language Diversity When Fine-Tuning Large Language Models for Translationaccepted
The Emperor’s New Reasoning: Format Imitation Overshadows Genuine Mathematical Understanding in SFTaccepted
The Enemy from Within: A Study of Political Delegitimization Discourse in Israeli Political Speechaccepted
The Face of Persuasion: Analyzing Bias and Generating Culture-Aware Adsaccepted
The Good, the Bad and the Constructive: Automatically Measuring Peer Review’s Utility for Authorsaccepted
The Good, the Bad, and the Debatable: A Survey on the Impacts of Data for In-Context Learningaccepted
The Green KNIGHT: Green Machine Translation with Knowledge-Distilled, Narrow, Inexpensive, Greedy, Hybrid Transformersaccepted
The Hallucination Tax of Reinforcement Finetuningaccepted
The Hidden Strength of Disagreement: Unraveling the Consensus-Diversity Tradeoff in Adaptive Multi-Agent Systemsaccepted
The Illusion of Progress: Re-evaluating Hallucination Detection in LLMsaccepted
The Illusion of Randomness: How LLMs Fail to Emulate Stochastic Decision-Making in Rock-Paper-Scissors Games?accepted
The Impact of Language Mixing on Bilingual LLM Reasoningaccepted
The Impact of Negated Text on Hallucination with Large Language Modelsaccepted
The LLM Already Knows: Estimating LLM-Perceived Question Difficulty via Hidden Representationsaccepted
The Language of Interoception: Examining Embodiment and Emotion Through a Corpus of Body Part Mentionsaccepted
The Medium Is Not the Message: Deconfounding Document Embeddings via Linear Concept Erasureaccepted
The Missing Parts: Augmenting Fact Verification with Half Truth Detectionaccepted
The More, The Better? A Critical Study of Multimodal Context in Radiology Report Summarizationaccepted
The Power of Framing: How News Headlines Guide Search Behavioraccepted
The Practical Impacts of Theoretical Constructs on Empathy Modelingaccepted
The Price of Format: Diversity Collapse in LLMsaccepted
The Progress Illusion: Revisiting meta-evaluation standards of LLM evaluatorsaccepted
The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Modelsaccepted
The Psychology of Falsehood: A Human-Centric Survey of Misinformation Detectionaccepted
The Pursuit of Empathy: Evaluating Small Language Models for PTSD Dialogue Supportaccepted
The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systemsaccepted
The Ranking Blind Spot: Decision Hijacking in LLM-based Text Rankingaccepted
The Role of Model Confidence on Bias Effects in Measured Uncertainties for Vision-Language Modelsaccepted
The Role of Outgoing Connection Heterogeneity in Feedforward Layers of Large Language Modelsaccepted
The Search for Conflicts of Interest: Open Information Extraction in Scientific Publicationsaccepted
The Security Threat of Compressed Projectors in Large Vision-Language Modelsaccepted
The Sound of Syntax: Finetuning and Comprehensive Evaluation of Language Models for Speech Pathologyaccepted
The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmasaccepted
The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating Itaccepted
The Stepwise Deception: Simulating the Evolution from True News to Fake News with LLM Agentsaccepted
The Strawberry Problem: Emergence of Character-level Understanding in Tokenized Language Modelsaccepted
The Transfer Neurons Hypothesis: An Underlying Mechanism for Language Latent Space Transitions in Multilingual LLMsaccepted
The Validation Gap: A Mechanistic Analysis of How Language Models Compute Arithmetic but Fail to Validate Itaccepted
The discordance between embedded ethics and cultural inference in large language modelsaccepted
The “r” in “woman” stands for rights. Auditing LLMs in Uncovering Social Dynamics in Implicit Misogynyaccepted
Theorem-Validated Reverse Chain-of-Thought Problem Generation for Geometric Reasoningaccepted
Think Clearly: Improving Reasoning via Redundant Token Pruningaccepted
Think Globally, Group Locally: Evaluating LLMs Using Multi-Lingual Word Grouping Gamesaccepted
Think Right, Not More: Test-Time Scaling for Numerical Claim Verificationaccepted
Think Twice, Generate Once: Safeguarding by Progressive Self-Reflectionaccepted
Think Wider, Detect Sharper: Reinforced Reference Coverage for Document-Level Self-Contradiction Detectionaccepted
Think and Recall: Layer-Level Prompting for Lifelong Model Editingaccepted
Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Modelaccepted
Think, Verbalize, then Speak: Bridging Complex Thoughts and Comprehensible Speechaccepted
ThinkAnswer Loss: Balancing Semantic Similarity and Exact Matching for LLM Reasoning Enhancementaccepted
ThinkEdit: Interpretable Weight Editing to Mitigate Overly Short Thinking in Reasoning Modelsaccepted
ThinkQE: Query Expansion via an Evolving Thinking Processaccepted
ThinkSLM: Towards Reasoning in Small Language Modelsaccepted
ThinkSwitcher: When to Think Hard, When to Think Fastaccepted
ThinkTuning: Instilling Cognitive Reflections without Distillationaccepted
Thinking Before You Speak: A Proactive Test-time Scaling Approachaccepted
Thinking Out Loud: Do Reasoning Models Know When They’re Right?accepted
Third-Person Appraisal Agent: Simulating Human Emotional Reasoning in Text with Large Language Modelsaccepted
This is not a Disimprovement: Improving Negation Reasoning in Large Language Models via Prompt Engineeringaccepted
Thought calibration: Efficient and confident test-time scalingaccepted
ThoughtProbe: Classifier-Guided LLM Thought Space Exploration via Probing Representationsaccepted
Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generationaccepted
Threading the Needle: Reweaving Chain-of-Thought Reasoning to Explain Human Label Variationaccepted
Through the Valley: Path to Effective Long CoT Training for Small Language Modelsaccepted
Thunder-DeID: Accurate and Efficient De-identification Framework for Korean Court Judgmentsaccepted
Time to Revisit Exact Matchaccepted
Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Gamesaccepted
Tiny Budgets, Big Gains: Parameter Placement Strategy in Parameter Super-Efficient Fine-Tuningaccepted
TinySQL: A Progressive Text-to-SQL Dataset for Mechanistic Interpretability Researchaccepted
To Answer or Not to Answer (TAONA): A Robust Textual Graph Understanding and Question Answering Approachaccepted
To Mask or to Mirror: Human-AI Alignment in Collective Reasoningaccepted
To See a World in a Spark of Neuron: Disentangling Multi-Task Interference for Training-Free Model Mergingaccepted
ToDi: Token-wise Distillation via Fine-Grained Divergence Controlaccepted
ToM-SSI: Evaluating Theory of Mind in Situated Social Interactionsaccepted
ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Modelsaccepted
Token Knowledge: A New Perspective For Knowledge in Large Language Modelsaccepted
Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigationaccepted
Token-Aware Editing of Internal Activations for Large Language Model Alignmentaccepted
Token-Level Metrics for Detecting Incorrect Gold Annotations in Named Entity Recognitionaccepted
Token-level Proximal Policy Optimization for Query Generationaccepted
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selectionaccepted
TokenSkip: Controllable Chain-of-Thought Compression in LLMsaccepted
Tokenization and Representation Biases in Multilingual Models on Dialectal NLP Tasksaccepted
TombRaider: Entering the Vault of History to Jailbreak Large Language Modelsaccepted
ToneCraft: Cantonese Lyrics Generation with Harmony of Tones and Pitchesaccepted
Too Consistent to Detect: A Study of Self-Consistent Errors in LLMsaccepted
Too Helpful, Too Harmless, Too Honest or Just Right?accepted
Tool Preferences in Agentic LLMs are Unreliableaccepted
Tool Zero: Training Tool-Augmented LLMs via Pure RL from Scratchaccepted
ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactionsaccepted
ToolSafety: A Comprehensive Dataset for Enhancing Safety in LLM-Based Agent Tool Invocationsaccepted
Toolscaler: Scalable Generative Tool Calling via Structure-Aware Semantic Tokenizationaccepted
TopXGen: Topic-Diverse Parallel Data Generation for Low-Resource Machine Translationaccepted
Topic Coverage-based Demonstration Retrieval for In-Context Learningaccepted
Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarizationaccepted
TopicAttack: An Indirect Prompt Injection Attack via Topic Transitionaccepted
TounsiBench: Benchmarking Large Language Models for Tunisian Arabicaccepted
Toward Efficient Sparse Autoencoder-Guided Steering for Improved In-Context Learning in Large Language Modelsaccepted
Toward Inclusive Language Models: Sparsity-Driven Calibration for Systematic and Interpretable Mitigation of Social Biases in LLMsaccepted
Toward Machine Interpreting: Lessons from Human Interpreting Studiesaccepted
Toward Machine Translation Literacy: How Lay Users Perceive and Rely on Imperfect Translationsaccepted
Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit Reasoningaccepted
Toward Optimal LLM Alignments Using Two-Player Gamesaccepted
Toward the Automatic Detection of Word Meaning Negotiation Indicators in Conversationaccepted
Towards AI-Assisted Psychotherapy: Emotion-Guided Generative Interventionsaccepted
Towards Achieving Concept Completeness for Textual Concept Bottleneck Modelsaccepted
Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Provingaccepted
Towards Author-informed NLP: Mind the Social Biasaccepted
Towards Automated Error Discovery: A Study in Conversational AIaccepted
Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Surveyaccepted
Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationalesaccepted
Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extractionaccepted
Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Modelsaccepted
Towards General-Domain Word Sense Disambiguation: Distilling Large Language Model into Compact Disambiguatoraccepted
Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Surveyaccepted
Towards Infinite-Long Prefix in Transformeraccepted
Towards Language-Agnostic STIPA: Universal Phonetic Transcription to Support Language Documentation at Scaleaccepted
Towards Low-Resource Alignment to Diverse Perspectives with Sparse Feedbackaccepted
Towards More Efficient Post-training via Fourier Domain Adapter Frameworkaccepted
Towards Multi-Document Question Answering in Scientific Literature: Pipeline, Dataset, and Evaluationaccepted
Towards Optimal Evaluation Efficiency for Large Language Modelsaccepted
Towards Personalized Conversational Sales Agents: Contextual User Profiling for Strategic Actionaccepted
Towards Reverse Engineering of Language Models: A Surveyaccepted
Towards Robust Few-Shot Relation Classification: Incorporating Relation Description with Agreementaccepted
Towards Robust Mathematical Reasoningaccepted
Towards Statistical Factuality Guarantee for Large Vision-Language Modelsaccepted
Towards Transferable Personality Representation Learning based on Triplet Comparisons and Its Applicationsaccepted
Towards Universal Debiasing for Language Models-based Tabular Data Generationaccepted
Towards a Holistic and Automated Evaluation Framework for Multi-Level Comprehension of LLMs in Book-Length Contextsaccepted
Towards a Unified Paradigm of Concept Editing in Large Language Modelsaccepted
Towards the Roots of the Negation Problem: A Multilingual NLI Dataset and Model Scaling Analysisaccepted
Toxicity Red-Teaming: Benchmarking LLM Safety in Singapore’s Low-Resource Languagesaccepted
TrInk: Ink Generation with Transformer Networkaccepted
TracSum: A New Benchmark for Aspect-Based Summarization with Sentence-Level Traceability in Medical Domainaccepted
Tracing L1 Interference in English Learner Writing: A Longitudinal Corpus with Error Annotationsaccepted
Tracing Multilingual Factual Knowledge Acquisition in Pretrainingaccepted
Tracing Training Footprints: A Calibration Approach for Membership Inference Attacks Against Multimodal Large Language Modelsaccepted
Train It and Forget It: Merge Lists are Unnecessary for BPE Inference in Language Modelsaccepted
Train Once for All: A Transitional Approach for Efficient Aspect Sentiment Triplet Extractionaccepted
Train One Sparse Autoencoder Across Multiple Sparsity Budgets to Preserve Interpretability and Accuracyaccepted
Train a Unified Multimodal Data Quality Classifier with Synthetic Dataaccepted
Training LLMs for Optimization Modeling via Iterative Data Synthesis and Structured Validationaccepted
Training LLMs to be Better Text Embedders through Bidirectional Reconstructionaccepted
Training Language Models to Critique With Multi-agent Feedbackaccepted
Training Medical QA Models Based on Mixed Rewards from Multiple-Choice and Open-Ended Questionsaccepted
Training Text-to-Molecule Models with Context-Aware Tokenizationaccepted
Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Modelsaccepted
Training compute-optimal transformer encoder modelsaccepted
Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Roundingaccepted
TransAlign: Machine Translation Encoders are Strong Word Aligners, Tooaccepted
TransBERT: A Framework for Synthetic Translation in Domain-Specific Language Modelingaccepted
Transfer-Aware Data Selection for Domain Adaptation in Text Retrievalaccepted
Transferable Direct Prompt Injection via Activation-Guided MCMC Samplingaccepted
Transformer-Based Temporal Information Extraction and Application: A Reviewaccepted
Transitive self-consistency evaluation of NLI models without gold labelsaccepted
Translate Smart, not Hard: Cascaded Translation Systems with Quality-Aware Deferralaccepted
Translating Domain-Specific Terminology in Typologically-Diverse Languages: A Study in Tax and Financial Educationaccepted
Translation in the Hands of Many: Centering Lay Users in Machine Translation Interactionsaccepted
Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationeseaccepted
Transparent and Coherent Procedural Mistake Detectionaccepted
Transplant Then Regenerate: A New Paradigm for Text Data Augmentationaccepted
TrapDoc: Deceiving LLM Users by Injecting Imperceptible Phantom Tokens into Documentsaccepted
Treble Counterfactual VLMs: A Causal Approach to Hallucinationaccepted
Tree of Agents: Improving Long-Context Capabilities of Large Language Models through Multi-Perspective Reasoningaccepted
Tree-Structured Non-Autoregressive Decoding for Sequence-to-Sequence Text Generationaccepted
Tree-of-Quote Prompting Improves Factuality and Attribution in Multi-Hop and Medical Reasoningaccepted
TreeBoN: Enhancing Inference-Time Alignment with Speculative Tree-Search and Best-of-N Samplingaccepted
TreeRare: Syntax Tree-Guided Retrieval and Reasoning for Knowledge-Intensive Question Answeringaccepted
TreeReview: A Dynamic Tree of Questions Framework for Deep and Efficient LLM-based Scientific Peer Reviewaccepted
TriSPrompt: A Hierarchical Soft Prompt Model for Multimodal Rumor Detection with Incomplete Modalitiesaccepted
Triangulating LLM Progress through Benchmarks, Games, and Cognitive Testsaccepted
TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agentaccepted
TrojanWave: Exploiting Prompt Learning for Stealthy Backdoor Attacks on Large Audio-Language Modelsaccepted
Trojsten Benchmark: Evaluating LLM Problem-Solving in Slovak STEM Competition Problemsaccepted
Trust Me, I’m Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answeraccepted
Trustworthy Medical Question Answering: An Evaluation-Centric Surveyaccepted
Tuning Less, Prompting More: In-Context Preference Learning Pipeline for Natural Language Transformationaccepted
TurBLiMP: A Turkish Benchmark of Linguistic Minimal Pairsaccepted
TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Textaccepted
TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Routeaccepted
TurnBench-MS: A Benchmark for Evaluating Multi-Turn, Multi-Step Reasoning in Large Language Modelsaccepted
TurnaboutLLM: A Deductive Reasoning Benchmark from Detective Gamesaccepted
Turning Logic Against Itself: Probing Model Defenses Through Contrastive Questionsaccepted
Turning the Tide: Repository-based Code Reflectionaccepted
TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers’ Guidanceaccepted
Two Challenges, One Solution: Robust Multimodal Learning through Dynamic Modality Recognition and Enhancementaccepted
Two Heads Are Better Than One: Dual-Model Verbal Reflection at Inference-Timeaccepted
Two Steps from Hell: Compositionality on Chemical LMsaccepted
Type-Less yet Type-Aware Inductive Link Prediction with Pretrained Language Modelsaccepted
UI-Hawk: Unleashing the Screen Stream Understanding for Mobile GUI Agentsaccepted
UICOMPASS: UI Map Guided Mobile Task Automation via Adaptive Action Generationaccepted
UIOrchestra: Generating High-Fidelity Code from UI Designs with a Multi-agent Systemaccepted
UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting Targetsaccepted
ULTRABENCH: Benchmarking LLMs under Extreme Fine-grained Text Generationaccepted
UNCERTAINTY-LINE: Length-Invariant Estimation of Uncertainty for Large Language Modelsaccepted
UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generationaccepted
UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware Perspectiveaccepted
UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulationaccepted
URO-Bench: Towards Comprehensive Evaluation for End-to-End Spoken Dialogue Modelsaccepted
UTMath: A Benchmark for Math Evaluation with Unit Testaccepted
UltraIF: Advancing Instruction Following from the Wildaccepted
UnCo: Uncertainty-Driven Collaborative Framework of Large and Small Models for Grounded Multimodal NERaccepted
Uncertainty-Aware Answer Selection for Improved Reasoning in Multi-LLM Systemsaccepted
Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Modelsaccepted
Uncovering Argumentative Flow: A Question-Focus Discourse Structuring Frameworkaccepted
Uncovering Factor-Level Preference to Improve Human-Model Alignmentaccepted
Uncovering Scaling Laws for Large Language Models via Inverse Problemsaccepted
Uncovering the Bigger Picture: Comprehensive Event Understanding Via Diverse News Retrievalaccepted
Under the Shadow of Babel: How Language Shapes Reasoning in LLMsaccepted
Understanding GUI Agent Localization Biases through Logit Sharpnessaccepted
Understanding How Value Neurons Shape the Generation of Specified Values in LLMsaccepted
Understanding LLMs’ Cross-Lingual Context Retrieval: How Good It Is And Where It Comes Fromaccepted
Understanding Refusal in Language Models with Sparse Autoencodersaccepted
Understanding Subword Compositionality of Large Language Modelsaccepted
Understanding and Improving Information Preservation in Prompt Compression for LLMsaccepted
Understanding and Leveraging the Expert Specialization of Context Faithfulness in Mixture-of-Experts LLMsaccepted
Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundaryaccepted
Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systemsaccepted
Understanding the Language Model to Solve the Symbolic Multi-Step Reasoning Problem from the Perspective of Buffer Mechanismaccepted
Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Modelsaccepted
Understanding the Thinking Process of Reasoning Models: A Perspective from Schoenfeld’s Episode Theoryaccepted
Unearthing Gems from Stones: Policy Optimization with Negative Sample Augmentation for LLM Reasoningaccepted
Unequal Scientific Recognition in the Age of LLMsaccepted
UniCoM: A Universal Code-Switching Speech Generatoraccepted
UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debuggingaccepted
UniRAG: A Unified RAG Framework for Knowledge-Intensive Queries with Decomposition, Break-Down Reasoning, and Iterative Rewritingaccepted
UniSpeaker: A Unified Approach for Multimodality-driven Speaker Generationaccepted
UnifiedVisual: A Framework for Constructing Unified Vision-Language Datasetsaccepted
Uniform Information Density and Syntactic Reduction: Revisiting *that*-Mentioning in English Complement Clausesaccepted
Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inferenceaccepted
UnitCoder: Scalable Code Synthesis from Pre-training Corporaaccepted

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.