ACL 2025 Accepted Papers

The full list of 3,086 papers accepted at ACL 2025 (Association for Computational Linguistics). Click any title for details, similar papers, and links to the original source. You can also search these papers by meaning, not just keywords.

Long: 1,602finding: 1,387Short: 97

Evaluating Visual and Cultural Interpretation: The K-Viscuit Benchmark with Human-VLM CollaborationLong
Evaluating the Evaluation of Diversity in Commonsense GenerationLong
Evaluating the Long-Term Memory of Large Language Modelsfinding
Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative ModelsLong
Evaluation of Attribution Bias in Generator-Aware Retrieval-Augmented Large Language Modelsfinding
Evaluation of LLM Vulnerabilities to Being Misused for Personalized Disinformation GenerationLong
Evaluation of LLMs in Medical Text Summarization: The Role of Vocabulary Adaptation in High OOV Settingsfinding
Event Pattern-Instance Graph: A Multi-Round Role Representation Learning Strategy for Document-Level Event Argument Extractionfinding
EventRAG: Enhancing LLM Generation with Event Knowledge GraphsLong
EvoBench: Towards Real-world LLM-Generated Text Detection Benchmarking for Evolving Large Language Modelsfinding
EvoWiki: Evaluating LLMs on Evolving KnowledgeLong
EvolveBench: A Comprehensive Benchmark for Assessing Temporal Awareness in LLMs on Evolving KnowledgeLong
ExPerT: Effective and Explainable Evaluation of Personalized Long-Form Text Generationfinding
Exclusion of Thought: Mitigating Cognitive Load in Large Language Models for Enhanced Reasoning in Multiple-Choice TasksLong
Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansionfinding
ExpeTrans: LLMs Are Experiential Transfer LearnersLong
Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agentfinding
Explain then Rank: Scale Calibration of Neural Rankers Using Natural Language Explanations from LLMsfinding
Explain-then-Process: Using Grammar Prompting to Enhance Grammatical Acceptability Judgmentsfinding
Explainable Depression Detection in Clinical Interviews with Personalized Retrieval-Augmented Generationfinding
Explainable Hallucination through Natural Language Inference Mappingfinding
Explaining Matters: Leveraging Definitions and Semantic Expansion for Sexism DetectionLong
Explaining Puzzle Solutions in Natural Language: An Exploratory Study on 6x6 Sudokufinding
ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Modelsfinding
Explicit Bayesian Inference to Uncover the Latent Themes of Large Language Modelsfinding
Explicit and Implicit Data Augmentation for Social Event DetectionLong
Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflectionfinding
Exploiting Contextual Knowledge in LLMs through 𝒱-usable Information based Layer EnhancementLong
Exploiting Instruction-Following Retrievers for Malicious Information Retrievalfinding
Exploiting Phonetics and Glyph Representation at Radical-level for Classical Chinese Understandingfinding
Exploiting the Shadows: Unveiling Privacy Leaks through Lower-Ranked Tokens in Large Language ModelsLong
ExploraCoder: Advancing Code Generation for Multiple Unseen APIs via Planning and Chained ExplorationLong
Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agentsfinding
Exploring Compositional Generalization of Multimodal LLMs for Medical ImagingLong
Exploring Explanations Improves the Robustness of In-Context LearningLong
Exploring Forgetting in Large Language Model Pre-TrainingLong
Exploring Graph Representations of Logical Forms for Language Modelingfinding
Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision EncoderLong
Exploring In-Image Machine Translation with Real-World Backgroundfinding
Exploring In-context Example Generation for Machine Translationfinding
Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversionfinding
Exploring Knowledge Filtering for Retrieval-Augmented Discriminative Tasksfinding
Exploring LLM Annotation for Adaptation of Clinical Information Extraction Models under Data-sharing Restrictionsfinding
Exploring LLMs’ Ability to Spontaneously and Conditionally Modify Moral Expressions through Text ManipulationLong
Exploring Layer-wise Representations of English and Chinese Homonymy in Pre-trained Language Modelsfinding
Exploring Multi-Modal Data with Tool-Augmented LLM Agents for Precise Causal Discoveryfinding
Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findingsfinding
Exploring Multimodal Relation Extraction of Hierarchical Tabular Data with Multi-task LearningLong
Exploring Persona Sentiment Sensitivity in Personalized Dialogue GenerationLong
Exploring Supervised Approaches to the Detection of Anthropomorphic Language in the Reporting of NLP Venuesfinding
Exploring the Choice Behavior of Large Language Modelsfinding
Exploring the Impact of Instruction-Tuning on LLM’s Susceptibility to MisinformationLong
Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and AnalysisLong
Exploring the Role of Mental Health Conversational Agents in Training Medical Students and Professionals: A Systematic Literature Reviewfinding
Exposing Numeracy Gaps: A Benchmark to Evaluate Fundamental Numerical Abilities in Large Language Modelsfinding
Exposing the Achilles’ Heel: Evaluating LLMs Ability to Handle Mistakes in Mathematical ReasoningLong
Express What You See: Can Multimodal LLMs Decode Visual Ciphers with Intuitive Semiosis Comprehension?finding
Extending Complex Logical Queries on Uncertain Knowledge GraphsLong
Extending LLM Context Window with Adaptive Grouped Positional Encoding: A Training-Free MethodLong
F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow MatchingLong
FACT-AUDIT: An Adaptive Multi-Agent Framework for Dynamic Fact-Checking Evaluation of Large Language ModelsLong
FADE: Why Bad Descriptions Happen to Good Featuresfinding
FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Onlyfinding
FCMR: Robust Evaluation of Financial Cross-Modal Multi-Hop ReasoningLong
FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature ImplementationLong
FEAT: A Preference Feedback Dataset through a Cost-Effective Auto-Generation and Labeling Framework for English AI TutoringShort
FGDGNN: Fine-Grained Dynamic Graph Neural Network for Rumor Detection on Social Mediafinding
FIHA: Automated Fine-grained Hallucinations Evaluations in Large Vision Language Models with Davidson Scene Graphsfinding
FLAG-TRADER: Fusion LLM-Agent with Gradient-based Reinforcement Learning for Financial Tradingfinding
FOCUS: Evaluating Pre-trained Vision-Language Models on Underspecification ReasoningLong
FPE2M2: Approaching Lossless and Efficient Quantization with Native Floating Pointfinding
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative SamplingLong
FRACTAL: Fine-Grained Scoring from Aggregate Text LabelsLong
FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphsfinding
FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategyfinding
FRAME: Feedback-Refined Agent Methodology for Enhancing Medical Research Insightsfinding
FREE: Fast and Robust Vision Language Models with Early Exitsfinding
FaVe: Factored and Verified Search Rationale for Long-form Answerfinding
Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completionfinding
FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality EvaluationLong
FactLens: Benchmarking Fine-Grained Fact Verificationfinding
Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentationfinding
FairI Tales: Evaluation of Fairness in Indian Contexts with a Focus on Bias and StereotypesLong
FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steeringfinding
Fairness Beyond Performance: Revealing Reliability Disparities Across Groups in Legal NLPLong
Fairness through Difference Awareness: Measuring Desired Group Discrimination in LLMsLong
Faithful and Robust LLM-Driven Theorem Proving for NLI ExplanationsLong
FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented GenerationLong
FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysisfinding
Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question AnsweringShort
Fast-and-Frugal Text-Graph Transformers are Effective Link Predictorsfinding
FastDraft: How to Train Your Draftfinding
FastMCTS: A Simple Sampling Strategy for Data SynthesisLong
Faster Speculative Decoding via Effective Draft Decoder with Pruned Candidate TreeLong
Feature-Level Insights into Artificial Text Detection with Sparse Autoencodersfinding
FedDQC: Data Quality Control in Federated Instruction-tuning of Large Language Modelsfinding
FedEx-LoRA: Exact Aggregation for Federated and Efficient Fine-Tuning of Large Language ModelsLong
FedLEKE: Federated Locate-then-Edit Knowledge Editing for Multi-Client Collaborationfinding
Federated Data-Efficient Instruction Tuning for Large Language Modelsfinding
FiDeLiS: Faithful Reasoning in Large Language Models for Knowledge Graph Question Answeringfinding
Filling the Temporal Void: Recovering Missing Publication Years in the Project Gutenberg Corpus Using LLMsfinding
FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning EvaluationLong
FinRipple: Aligning Large Language Models with Financial Market for Event Ripple Effect Awarenessfinding
FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and ChallengingLong
Financial Language Model Evaluation (FLaME)finding
Finding A Voice: Exploring the Potential of African American Dialect and Voice Generation for ChatbotsLong
Finding Needles in Images: Can Multi-modal LLMs Locate Fine Details?Long
Finding the Sweet Spot: Preference Data Construction for Scaling Preference OptimizationLong
Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMsLong
Fine-grained Knowledge Enhancement for Retrieval-Augmented Generationfinding
Fine-grained Video Dubbing Duration Alignment with Segment Supervised Preference OptimizationLong
FineCite: A Novel Approach For Fine-Grained Citation Context Analysisfinding
FineReason: Evaluating and Improving LLMs’ Deliberate Reasoning through Reflective Puzzle SolvingLong
Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State TrackingLong
Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactionsfinding
First-Step Advantage: Importance of Starting Right in Multi-Step Math Reasoningfinding
FitCF: A Framework for Automatic Feature Importance-guided Counterfactual Example Generationfinding
Fixing Distribution Shifts of LLM Self-Critique via On-Policy Self-Play TrainingLong
FlashAudio: Rectified Flow for Fast and High-Fidelity Text-to-Audio GenerationLong
FlashBack: Efficient Retrieval-Augmented Language Modeling for Fast Inferencefinding
Flexora: Flexible Low-Rank Adaptation for Large Language ModelsLong
Flipping Knowledge Distillation: Leveraging Small Models’ Expertise to Enhance LLMs in Text MatchingLong
FloorPlan-LLaMa: Aligning Architects’ Feedback and Domain Knowledge in Architectural Floor Plan GenerationLong
Flow2Code: Evaluating Large Language Models for Flowchart-based Code Generation Capabilityfinding
Flowchart-Based Decision Making with Large Language Modelsfinding
FocalPO: Enhancing Preference Optimizing by Focusing on Correct Preference RankingsShort
Focus on What Matters: Enhancing Medical Vision-Language Models with Automatic Attention Alignment TuningLong
FocusLLM: Precise Understanding of Long Context by Dynamic CondensingLong
Focused-DPO: Enhancing Code Generation Through Focused Preference Optimization on Error-Prone Pointsfinding
FoldMoE: Efficient Long Sequence MoE Training via Attention-MoE PipeliningLong
Follow-up Question Generation For Enhanced Patient-Provider ConversationsLong
Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Modelsfinding
Forgotten Polygons: Multimodal Large Language Models are Shape-Blindfinding
Forward Knows Efficient Backward Path: Saliency-Guided Memory-Efficient Fine-tuning of Large Language ModelsLong
Fraud-R1 : A Multi-Round Benchmark for Assessing the Robustness of LLM Against Augmented Fraud and Phishing Inducementsfinding
Frequency matters: Modeling irregular morphological patterns in Spanish with Transformersfinding
Frictional Agent Alignment Framework: Slow Down and Don’t Break ThingsLong
From Awareness to Adaptability: Enhancing Tool Utilization for Scientific Reasoningfinding
From Citations to Criticality: Predicting Legal Decision Influence in the Multilingual Swiss JurisprudenceShort
From Complexity to Clarity: AI/NLP’s Role in Regulatory Compliancefinding
From Conversation to Automation: Leveraging LLMs for Problem-Solving Therapy Analysisfinding
From English to Second Language Mastery: Enhancing LLMs with Cross-Lingual Continued Instruction TuningLong
From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMsfinding
From Heart to Words: Generating Empathetic Responses via Integrated Figurative Language and Semantic Context Signalsfinding
From Human Reading to NLM Understanding: Evaluating the Role of Eye-Tracking Data in Encoder-Based ModelsLong
From Imitation to Introspection: Probing Self-Consciousness in Language Modelsfinding
From Informal to Formal – Incorporating and Evaluating LLMs on Natural Language Requirements to Verifiable Formal ProofsLong
From Information to Insight: Leveraging LLMs for Open Aspect-Based Educational SummarizationLong
From Isolates to Families: Using Neural Networks for Automated Language AffiliationLong
From Lists to Emojis: How Format Bias Affects Model AlignmentLong
From Misleading Queries to Accurate Answers: A Three-Stage Fine-Tuning Method for LLMsfinding
From Neurons to Semantics: Evaluating Cross-Linguistic Alignment Capabilities of Large Language Models via Neurons AlignmentLong
From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question GenerationLong
From Observation to Understanding: Front-Door Adjustments with Uncertainty Calibration for Enhancing Egocentric Reasoning in LVLMsfinding
From Outcomes to Processes: Guiding PRM Learning from ORM for Inference-Time AlignmentLong
From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understandingfinding
From Perceptions to Decisions: Wildfire Evacuation Decision Prediction with Behavioral Theory-informed LLMsLong
From Phrases to Subgraphs: Fine-Grained Semantic Parsing for Knowledge Graph Question Answeringfinding
From Real to Synthetic: Synthesizing Millions of Diversified and Complicated User Instructions with Attributed GroundingLong
From Selection to Generation: A Survey of LLM-based Active LearningLong
From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalitiesfinding
From Sub-Ability Diagnosis to Human-Aligned Generation: Bridging the Gap for Text Length Control via MarkerGenLong
From Tools to Teammates: Evaluating LLMs in Multi-Session Coding InteractionsLong
From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language ModelsLong
Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoningfinding
Fusing Highly Specialized Language Models for Comprehensive ExpertiseLong
Fuzzy Speculative Decoding for a Tunable Accuracy-Runtime Tradeofffinding
G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent SystemsLong
G2S: A General-to-Specific Learning Framework for Temporal Knowledge Graph Forecasting with Large Language Modelsfinding
GA-S3: Comprehensive Social Network Simulation with Group Agentsfinding
GALLa: Graph Aligned Large Language Models for Improved Source Code UnderstandingLong
GAMEBoT: Transparent Assessment of LLM Reasoning in GamesLong
GAPO: Learning Preferential Prompt through Generative Adversarial Policy OptimizationLong
GEMS: Generation-Based Event Argument Extraction via Multi-perspective Prompts and Ontology Steeringfinding
GETReason: Enhancing Image Context Extraction through Hierarchical Multi-Agent ReasoningLong
GIFT-SW: Gaussian noise Injected Fine-Tuning of Salient Weights for LLMsLong
GIMMICK: Globally Inclusive Multimodal Multitask Cultural Knowledge Benchmarkingfinding
GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completionfinding
GLiM: Integrating Graph Transformer and LLM for Document-Level Biomedical Relation Extraction with Incomplete Labelingfinding
GNN-RAG: Graph Neural Retrieval for Efficient Large Language Model Reasoning on Knowledge Graphsfinding
GODBench: A Benchmark for Multimodal Large Language Models in Video Comment ArtLong
GOLFer: Smaller LMs-Generated Documents Hallucination Filter & Combiner for Query Expansion in Information Retrievalfinding
GOODLIAR: A Reinforcement Learning-Based Deceptive Agent for Disrupting LLM Beliefs on Foundational Principlesfinding
GPT-4 as a Homework Tutor Can Improve Student Engagement and Learning OutcomesLong
GRACE: A Granular Benchmark for Evaluating Model Calibration against Human CalibrationLong
GRAF: Graph Retrieval Augmented by Facts for Romanian Legal Multi-Choice Question Answeringfinding
GRAM: Generative Recommendation via Semantic-aware Multi-granular Late FusionLong
GRAMMAR-LLM: Grammar-Constrained Natural Language Generationfinding
GRAT: Guiding Retrieval-Augmented Reasoning through Process Rewards Tree SearchLong
GRI-QA: a Comprehensive Benchmark for Table Question Answering over Environmental Datafinding
GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Modelsfinding
GRaMPa: Subword Regularisation by Skewing Uniform Segmentation Distributions with an Efficient Path-counting Markov ModelLong
GSQ-Tuning: Group-Shared Exponents Integer in Fully Quantized Training for LLMs On-Device Fine-tuningfinding
GUI Agents: A Surveyfinding
GUI-explorer: Autonomous Exploration and Mining of Transition-aware Knowledge for GUI AgentLong
GUICourse: From General Vision Language Model to Versatile GUI AgentLong
GUIDEX: Guided Synthetic Data Generation for Zero-Shot Information Extractionfinding
GUM-SAGE: A Novel Dataset and Approach for Graded Entity Salience Predictionfinding
GaRAGe: A Benchmark with Grounding Annotations for RAG Evaluationfinding
GainRAG: Preference Alignment in Retrieval-Augmented Generation through Gain Signal SynthesisLong
Game Development as Human-LLM InteractionLong
GeAR: Generation Augmented Retrievalfinding
GeAR: Graph-enhanced Agent for Retrieval-augmented Generationfinding
GeLLM³O: Generalizing Large Language Models for Multi-property Molecule OptimizationLong
GeNRe: A French Gender-Neutral Rewriting System Using Collective Nounsfinding
GenKnowSub: Improving Modularity and Reusability of LLMs through General Knowledge SubtractionShort
GenTool: Enhancing Tool Generalization in Language Models through Zero-to-One and Weak-to-Strong Simulationfinding
Gender Inclusivity Fairness Index (GIFI): A Multilevel Framework for Evaluating Gender Diversity in Large Language ModelsLong
GenderAlign: An Alignment Dataset for Mitigating Gender Bias in Large Language ModelsLong
Generalizable Cross-Lingual Cognitive Distortion Detection with Standardized Annotations and Multi-Task Learningfinding
Generalized Attention Flow: Feature Attribution for Transformer Models via Maximum FlowLong
Generate First, Then Sample: Enhancing Fake News Detection with LLM-Augmented Reinforced SamplingLong
Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolutionfinding
Generating Diverse Training Samples for Relation Extraction with Large Language ModelsLong
Generating Domain-Specific Knowledge Graphs from Large Language Modelsfinding
Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Modelsfinding
Generating Plausible Distractors for Multiple-Choice Questions via Student Choice PredictionLong
Generating Questions, Answers, and Distractors for Videos: Exploring Semantic Uncertainty of Object Motionsfinding
Generative Error Correction for Emotion-aware Speech-to-text Translationfinding
Generative Frame Sampler for Long Video Understandingfinding
Generative Music Models’ Alignment with Professional and Amateur Users’ Expectationsfinding
Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language ModelsLong
Generative Reward Modeling via Synthetic Criteria Preference LearningLong
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced ReasoningLong
Geometric Signatures of Compositionality Across a Language Model’s LifetimeLong
GiFT: Gibbs Fine-Tuning for Code GenerationLong
GigaSpeech 2: An Evolving, Large-Scale and Multi-domain ASR Corpus for Low-Resource Languages with Automated Crawling, Transcription and RefinementLong
Global Eye: Breaking the “Fixed Thinking Pattern” during the Instruction Expansion ProcessLong
Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual EvaluationLong
GlyphPattern: An Abstract Pattern Recognition for Vision-Language Modelsfinding
Going Beyond Your Expectations in Latency Metrics for Simultaneous Speech Translationfinding
GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language ModelsLong
Gradient-Adaptive Policy Optimization: Towards Multi-Objective Alignment of Large Language ModelsLong
GrammaMT: Improving Machine Translation with Grammar-Informed In-Context LearningLong
Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?finding
Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM ReasoningLong
Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with GraphsLong
Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic languagesfinding
Graph-Structured Trajectory Extraction from TraveloguesLong
Graph-guided Cross-composition Feature Disentanglement for Compositional Zero-shot Learningfinding
GraphCheck: Breaking Long-Term Text Barriers with Extracted Knowledge Graph-Powered Fact-CheckingLong
GraphInsight: Unlocking Insights in Large Language Models for Graph Structure UnderstandingLong
GraphNarrator: Generating Textual Explanations for Graph Neural NetworksLong
Graphically Speaking: Unmasking Abuse in Social Media with Conversation InsightsLong
Grounded, or a Good Guesser? A Per-Question Balanced Dataset to Separate Blind from Grounded Models for Embodied Question AnsweringShort
Grounding Task Assistance with Multimodal Cues from a Single Demonstrationfinding
Group then Scale: Dynamic Mixture-of-Experts Multilingual Language Modelfinding
Growing Through Experience: Scaling Episodic Grounding in Language ModelsLong
GuessArena: Guess Who I Am? A Self-Adaptive Framework for Evaluating LLMs in Domain-Specific Knowledge and ReasoningLong
GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM AgentsLong
Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous ConstraintsLong
Gumbel Reranking: Differentiable End-to-End Reranker OptimizationLong
Gödel Agent: A Self-Referential Agent Framework for Recursively Self-ImprovementLong
HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI CoauthoringLong
HAF-RM: A Hybrid Alignment Framework for Reward Model TrainingLong
HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language ModelsLong
HALoGEN: Fantastic LLM Hallucinations and Where to Find ThemLong
HASH-RAG: Bridging Deep Hashing with Retriever for Efficient, Fine Retrieval and Augmented Generationfinding
HATA: Trainable and Hardware-Efficient Hash-Aware Top-k Attention for Scalable Large Model Inferencefinding
HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMsLong
HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text RetrievalLong
HFT: Half Fine-Tuning for Large Language ModelsLong
HG-InsightLog: Context Prioritization and Reduction for Question Answering with Non-Natural Language Construct Log Datafinding
HICD: Hallucination-Inducing via Attention Dispersion for Contrastive Decoding to Mitigate Hallucinations in Large Language Modelsfinding
HPSS: Heuristic Prompting Strategy Search for LLM Evaluatorsfinding
HSCR: Hierarchical Self-Contrastive Rewarding for Aligning Medical Vision Language ModelsLong
HTML: Hierarchical Topology Multi-task Learning for Semantic Parsing in Knowledge Base Question Answeringfinding
HalluLens: LLM Hallucination BenchmarkLong
Hallucination Detox: Sensitivity Dropout (SenD) for Large Language Model TrainingLong
HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Assistant Scenariosfinding
Hanging in the Balance: Pivotal Moments in Crisis Counseling ConversationsLong
Harnessing Large Language Models for Disaster Management: A Surveyfinding
Harnessing PDF Data for Improving Japanese Large Multimodal Modelsfinding
Harnessing Whisper for Prosodic Stress Analysisfinding
Has Machine Translation Evaluation Achieved Human Parity? The Human Reference and the Limits of ProgressShort
HateDay: Insights from a Global Hate Speech Dataset Representative of a Day on TwitterLong
HatePRISM: Policies, Platforms, and Research Integration. Advancing NLP for Hate Speech Proactive Mitigationfinding
Hatevolution: What Static Benchmarks Don’t Tell Usfinding
Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and RethinkingLong
HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense Reasoningfinding
Help Me Write a Story: Evaluating LLMs’ Ability to Generate Writing FeedbackLong
HelpSteer3: Human-Annotated Feedback and Edit Data to Empower Inference-Time Scaling in Open-Ended General-Domain TasksLong
Heuristic-based Search Algorithm in Automatic Instruction-focused Prompt Optimization: A Surveyfinding
HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language ModelLong
HiCOT: Improving Neural Topic Models via Optimal Transport and Contrastive Learningfinding
HiDe-LLaVA: Hierarchical Decoupling for Continual Instruction Tuning of Multimodal Large Language ModelLong
Hidden in Plain Sight: Evaluation of the Deception Detection Capabilities of LLMs in Multimodal SettingsLong
HiddenDetect: Detecting Jailbreak Attacks against Multimodal Large Language Models via Monitoring Hidden StatesLong
Hierarchical Attention Generates Better ProofsLong
Hierarchical Bracketing Encodings for Dependency Parsing as TaggingLong
Hierarchical Document Refinement for Long-context Retrieval-augmented GenerationLong
Hierarchical Level-Wise News Article Clustering via Multilingual Matryoshka EmbeddingsLong
Hierarchical Memory Organization for Wikipedia GenerationLong
Hierarchical Retrieval with Evidence Curation for Open-Domain Financial Question Answering on Standardized Documentsfinding
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Modelsfinding
Hierarchical-Task-Aware Multi-modal Mixture of Incremental LoRA Experts for Embodied Continual LearningLong
HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic ClaimsLong
HoH: A Dynamic Benchmark for Evaluating the Impact of Outdated Information on Retrieval-Augmented GenerationLong
HoPE: A Novel Positional Encoding Without Long-Term Decay for Enhanced Context Awareness and ExtrapolationLong
HomeBench: Evaluating LLMs in Smart Homes with Valid and Invalid Instructions Across Single and Multiple DevicesLong
HopRAG: Multi-Hop Reasoning for Logic-Aware Retrieval-Augmented Generationfinding
HotelMatch-LLM: Joint Multi-Task Training of Small and Large Language Models for Efficient Multimodal Hotel RetrievalLong
How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Trainingfinding
How Do Multilingual Language Models Remember Facts?finding
How Does Response Length Affect Long-Form Factualityfinding
How Far are LLMs from Being Our Digital Twins? A Benchmark for Persona-Based Behavior Chain Simulationfinding
How Humans and LLMs Organize Conceptual Knowledge: Exploring Subordinate Categories in ItalianLong
How LLMs Comprehend Temporal Meaning in Narratives: A Case Study in Cognitive Evaluation of LLMsLong
How Much Do Encoder Models Know About Word Senses?Long
How Numerical Precision Affects Arithmetical Reasoning Capabilities of LLMsfinding
How Personality Traits Shape LLM Risk-Taking Behaviourfinding
How Programming Concepts and Neurons Are Shared in Code Language Modelsfinding
How do LLMs’ Preferences Affect Event Argument Extraction? CAT: Addressing Preference Traps in Unsupervised EAEfinding
How do Transformer Embeddings Represent Compositions? A Functional Analysisfinding
How does Misinformation Affect Large Language Model Behaviors and Preferences?Long
How to Compare Things Properly? A Study of Argument Relevance in Comparative Question AnsweringLong
How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and BeyondLong
How to Mitigate Overfitting in Weak-to-strong Generalization?Long
How to Train Long-Context Language Models (Effectively)Long
HumT DumT: Measuring and controlling human-like language in LLMsLong
Human Alignment: How Much Do We Adapt to LLMs?Short
Human Bias in the Face of AI: Examining Human Judgment Against Text Labeled as AI Generatedfinding
Human-LLM Coevolution: Evidence from Academic Writingfinding
HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation Taskfinding
HyGenar: An LLM-Driven Hybrid Genetic Algorithm for Few-Shot Grammar Generationfinding
HyKGE: A Hypothesis Knowledge Graph Enhanced RAG Framework for Accurate and Reliable Medical LLMs ResponsesLong
HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge BasesLong
Hybrid Preferences: Learning to Route Instances for Human vs. AI FeedbackLong
HyperCRS: Hypergraph-Aware Multi-Grained Preference Learning to Burst Filter Bubbles in Conversational Recommendation Systemfinding
HyperFM: Fact-Centric Multimodal Fusion for Link Prediction over Hyper-Relational Knowledge GraphsLong
Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansionfinding
I see what you mean: Co-Speech Gestures for Reference Resolution in Multimodal Dialoguefinding
I0T: Embedding Standardization Method Towards Zero Modality GapLong
IAM: Efficient Inference through Attention Mapping between Different-scale LLMsLong
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMsLong
IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abductionfinding
IMOL: Incomplete-Modality-Tolerant Learning for Multi-Domain Fake News Video DetectionLong
IMPARA-GED: Grammatical Error Detection is Boosting Reference-free Grammatical Error Quality Estimatorfinding
INJONGO: A Multicultural Intent Detection and Slot-filling Dataset for 16 African LanguagesLong
INT: Establishing Information Transfer for Multilingual Intent Detection and Slot Fillingfinding
INTERACT: Enabling Interactive, Question-Driven Learning in Large Language ModelsLong
INVESTORBENCH: A Benchmark for Financial Decision-Making Tasks with LLM-based AgentLong
IOPO: Empowering LLMs with Complex Instruction Following via Input-Output Preference OptimizationLong
IPO: Your Language Model is Secretly a Preference ClassifierLong
IRIS: An Iterative and Integrated Framework for Verifiable Causal Discovery in the Absence of Tabular DataLong
IRIS: Interpretable Retrieval-Augmented Classification for Long Interspersed Document SequencesLong
IRT-Router: Effective and Interpretable Multi-LLM Routing via Item Response TheoryLong
ISR: Self-Refining Referring Expressions for Entity GroundingLong
IW-Bench: Evaluating Large Multimodal Models for Converting Image-to-Webfinding
Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language ModelsLong
Identifying Open Challenges in Language IdentificationLong
Identifying Reliable Evaluation Metrics for Scientific Text RevisionLong
If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?Long
If Eleanor Rigby Had Met ChatGPT: A Study on Loneliness in a Post-LLM WorldLong
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMsLong
Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Modelsfinding
Impartial Multi-task Representation Learning via Variance-invariant Probabilistic DecodingLong
ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in VideosLong
Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignmentfinding
Implicit Reasoning in Transformers is Reasoning through Shortcutsfinding
Improve Language Model and Brain Alignment via Associative Memoryfinding
Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimatefinding
Improve Safety Training of Large Language Models with Safety-Critical Singular Vectors LocalizationLong
Improve Vision Language Model Chain-of-thought ReasoningLong
Improved Unbiased Watermark for Large Language ModelsLong
Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-JudgeLong
Improving Causal Interventions in Amnesic Probing with Mean Projection or LEACEfinding
Improving Chain-of-Thought Reasoning via Quasi-Symbolic AbstractionsLong
Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced OptimizationLong
Improving Continual Pre-training Through Seamless Data Packingfinding
Improving Dialogue Discourse Parsing through Discourse-aware Utterance ClarificationLong
Improving Dialogue State Tracking through Combinatorial Search for In-Context ExamplesLong
Improving Efficiency in Large Language Models via Extendable Block Floating Point Representationfinding
Improving Factuality with Explicit Working MemoryLong
Improving Fairness of Large Language Models in Multi-document SummarizationShort
Improving Language and Modality Transfer in Translation by Character-level ModelingLong
Improving Low-Resource Morphological Inflection via Self-Supervised ObjectivesLong
Improving MLLM’s Document Image Machine Translation via Synchronously Self-reviewing Its OCR Proficiencyfinding
Improving Medical Large Vision-Language Models with Abnormal-Aware FeedbackLong
Improving Model Factuality with Fine-grained Critique-based EvaluatorLong
Improving Occupational ISCO Classification of Multilingual Swiss Job Postings with LLM-Refined Training Datafinding
Improving Parallel Sentence Mining for Low-Resource and Endangered LanguagesShort
Improving Preference Extraction In LLMs By Identifying Latent Knowledge Through Classifying ProbesLong
Improving Word Alignment Using Semi-Supervised Learningfinding
Improving the Calibration of Confidence Scores in Text Generation Using the Output Distribution’s CharacteristicsShort
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue AgentsLong
In Search of the Lost Arch in Dialogue: A Dependency Dialogue Acts Corpus for Multi-Party Dialoguesfinding
In the LLM era, Word Sense Induction remains unsolvedfinding
In-the-wild Audio Spatialization with Flexible Text-guided LocalizationLong
InImageTrans: Multimodal LLM-based Text Image Machine Translationfinding
InSerter: Speech Instruction Following with Unsupervised Interleaved Pre-trainingLong
Incongruity-aware Tension Field Network for Multi-modal Sarcasm DetectionLong
Inconsistent Tokenizations Cause Language Models to be Perplexed by Japanese GrammarShort
Incorporating Domain Knowledge into Materials TokenizationLong
IndicSynth: A Large-Scale Multilingual Synthetic Speech Dataset for Low-Resource Indian LanguagesLong
Inducing lexicons of in-group language with socio-temporal contextLong
InductionBench: LLMs Fail in the Simplest Complexity ClassLong
Inductive Linguistic Reasoning with Large Language Modelsfinding
Inference Compute-Optimal Video Vision Language ModelsLong
Inferring Functionality of Attention Heads from their ParametersLong
Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate SelectionLong
InfiniSST: Simultaneous Translation of Unbounded Speech with Large Language Modelfinding
InfiniteICL: Breaking the Limit of Context Window Size via Long Short-term Memory Transformationfinding
Influences on LLM Calibration: A Study of Response Agreement, Loss Functions, and Prompt StylesLong
Infogen: Generating Complex Statistical Infographics from DocumentsLong
Information Extraction from Visually Rich Documents using LLM-based Organization of Documents into Independent Textual SegmentsLong
Information Locality as an Inductive Bias for Neural Language ModelsLong
Initializing and Retrofitting Key-Value Adaptors for Traceable Model Editingfinding
Inner Thinking Transformer: Leveraging Dynamic Depth Scaling to Foster Adaptive Internal ThinkingLong
Innovative Image Fraud Detection with Cross-Sample Anomaly Analysis: The Power of LLMsLong
Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMsLong
InspireDebate: Multi-Dimensional Subjective-Objective Evaluation-Guided Reasoning and Optimization for DebatingLong
Instance-Selection-Inspired Undersampling Strategies for Bias Reduction in Small and Large Language Models for Binary Text ClassificationLong
InstructPart: Task-Oriented Part Segmentation with Instruction ReasoningLong
Instruction Tuning on Public Government and Cultural Data for Low-Resource Language: a Case Study in KazakhLong
Instruction-Tuning Data Synthesis from Scratch via Web Reconstructionfinding
Instruction-Tuning LLMs for Event Extraction with Annotation Guidelinesfinding
Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization on Multi-party ConversationLong
IntelliCockpitBench: A Comprehensive Benchmark to Evaluate VLMs for Intelligent Cockpitfinding
IntentionESC: An Intention-Centered Framework for Enhancing Emotional Support in Dialogue Systemsfinding
Inter-Passage Verification for Multi-evidence Multi-answer QAfinding
Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language ModelsLong
Interactive and Expressive Code-Augmented Planning with Large Language ModelsLong
Interlocking-free Selective Rationalization Through Genetic-based LearningLong
InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Modelfinding
Internal Value Alignment in Large Language Models through Controlled Value Vector ActivationLong
Internal and External Impacts of Natural Language Processing PapersShort
Interpret and Improve In-Context Learning via the Lens of Input-Label MappingsLong
Introducing Graph Context into Language Models through Parameter-Efficient Fine-Tuning for Lexical Relation MiningLong
Introducing Verification Task of Set Consistency with Set-Consistency Energy NetworksLong
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single ProcessLong
InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes Under Herd BehaviorLong
Investigating Context Faithfulness in Large Language Models: The Roles of Memory Strength and Evidence Stylefinding
Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Studyfinding
Investigating Language Preference of Multilingual RAG Systemsfinding
Investigating Prosodic Signatures via Speech Pre-Trained Models for Audio Deepfake Source Attributionfinding
Investigating and Enhancing Vision-Audio Capability in Omnimodal Large Language Modelsfinding
Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal InconsistencyLong
Investigating and Extending Homans’ Social Exchange Theory with Large Language Model based AgentsLong
Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Trainingfinding
Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial TrainingLong
Is External Information Useful for Stance Detection with LLMs?finding
Is It JUST Semantics? A Case Study of Discourse Particle Understanding in LLMsfinding
Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreementfinding
Is Large Language Model Performance on Reasoning Tasks Impacted by Different Ways Questions Are Asked?finding
Is That Your Final Answer? Test-Time Scaling Improves Selective Question AnsweringShort
Is a cute puyfred cute? Context-dependent form-meaning systematicity in LLMsfinding
Is linguistically-motivated data augmentation worth it?Long
Iterative Repair with Weak Verifiers for Few-shot Transfer in KBQA with Unanswerabilityfinding
It’s Not Bragging If You Can Back It Up: Can LLMs Understand Braggings?Long
It’s Not a Walk in the Park! Challenges of Idiom Translation in Speech-to-text SystemsLong
JARVIS-VLA: Post-Training Large-Scale Vision Language Models to Play Visual Games with Keyboards and Mousefinding
JEBS: A Fine-grained Biomedical Lexical Simplification Taskfinding
Jailbreak Large Vision-Language Models Through Multi-Modal LinkageLong
JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMsLong
Jailbreaking? One Step Is Enough!Long
JoPA: Explaining Large Language Model’s Generation via Joint Prompt AttributionLong
JsonTuning: Towards Generalizable, Robust, and Controllable Instruction Tuningfinding
JuStRank: Benchmarking LLM Judges for System RankingLong
Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Modelsfinding
Just Go Parallel: Improving the Multilingual Capabilities of Large Language ModelsLong
Just KIDDIN’ : Knowledge Infusion and Distillation for Detection of INdecent Memesfinding
Just Put a Human in the Loop? Investigating LLM-Assisted Annotation for Subjective Tasksfinding
Just a Scratch: Enhancing LLM Capabilities for Self-harm Detection through Intent Differentiation and Emoji InterpretationLong
K-order Ranking Preference Optimization for Large Language Modelsfinding
K/DA: Automated Data Generation Pipeline for Detoxifying Implicitly Offensive Language in KoreanLong
KAPA: A Deliberative Agent Framework with Tree-Structured Knowledge Base for Multi-Domain User Intent Understandingfinding
KARPA: A Training-free Method of Adapting Knowledge Graph as References for Large Language Model’s Reasoning Path Aggregationfinding
KE-MHISTO: Towards a Multilingual Historical Knowledge Extraction Benchmark for Addressing the Long-Tail Problemfinding
KERL: Knowledge-Enhanced Personalized Recipe Recommendation using Large Language ModelsLong
KG-Agent: An Efficient Autonomous Agent Framework for Complex Reasoning over Knowledge GraphLong
KITAB-Bench: A Comprehensive Multi-Domain Benchmark for Arabic OCR and Document Understandingfinding
KRISTEVA: Close Reading as a Novel Task for Benchmarking Interpretive ReasoningLong
KV-Latent: Dimensional-level KV Cache Reduction with Frequency-aware Rotary Positional EmbeddingLong
KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputationfinding
KaFT: Knowledge-aware Fine-tuning for Boosting LLMs’ Domain-specific Question-Answering Performancefinding
KatFishNet: Detecting LLM-Generated Korean Text through Linguistic Feature AnalysisLong
KazMMLU: Evaluating Language Models on Kazakh, Russian, and Regional Knowledge of KazakhstanLong
Keys to Robust Edits: From Theoretical Insights to Practical AdvancesLong
KiRAG: Knowledge-Driven Iterative Retriever for Enhancing Retrieval-Augmented GenerationLong
Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit ProfilesLong
Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability ModelingLong
Know the Unknown: An Uncertainty-Sensitive Method for LLM Instruction Tuningfinding
KnowCoder-X: Boosting Multilingual Information Extraction via Codefinding
KnowShiftQA: How Robust are RAG Systems when Textbook Knowledge Shifts in K-12 Education?Short
Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before Completionfinding
Knowledge Base Construction for Knowledge-Augmented Text-to-SQLfinding
Knowledge Boundary of Large Language Models: A SurveyLong
Knowledge Decoupling via Orthogonal Projection for Lifelong Editing of Large Language ModelsLong
Knowledge Graph Retrieval-Augmented Generation for LLM-based RecommendationLong
Knowledge Image Matters: Improving Knowledge-Based Visual Reasoning with Multi-Image Large Language ModelsLong
Knowledge Tracing in Programming Education Integrating Students’ QuestionsLong
Knowledge-Augmented Multimodal Clinical Rationale Generation for Disease Diagnosis with Small Language ModelsLong
KodCode: A Diverse, Challenging, and Verifiable Synthetic Dataset for Codingfinding
KokoroChat: A Japanese Psychological Counseling Dialogue Dataset Collected via Role-Playing by Trained CounselorsLong
Konooz: Multi-domain Multi-dialect Corpus for Named Entity Recognitionfinding
L-CiteEval: A Suite for Evaluating Fidelity of Long-context ModelsLong
L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language ModelsLong
LACA: Improving Cross-lingual Aspect-Based Sentiment Analysis with LLM Data AugmentationLong
LADDER: Language-Driven Slice Discovery and Error Rectification in Vision Classifiersfinding
LADM: Long-context Training Data Selection with Attention-based Dependency Measurement for LLMsLong
LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedbackfinding
LAMB: A Training-Free Method to Enhance the Long-Context Understanding of SSMs via Attention-Guided Token FilteringShort
LAQuer: Localized Attribution Queries in Content-grounded GenerationLong
LCFO: Long Context and Long Form Output Dataset and Benchmarkingfinding
LCHAIM - Investigating Long Context Reasoning in Hebrewfinding
LDIR: Low-Dimensional Dense and Interpretable Text Embeddings with Relative Representationsfinding
LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language ModelsLong
LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-DisjointLong
LEMMA: Learning from Errors for MatheMatical Advancement in LLMsfinding
LEMONADE: A Large Multilingual Expert-Annotated Abstractive Event Dataset for the Real Worldfinding
LESA: Learnable LLM Layer Scaling-UpLong
LETS-C: Leveraging Text Embedding for Time Series ClassificationLong
LGAR: Zero-Shot LLM-Guided Neural Ranking for Abstract Screening in Systematic Literature Reviewsfinding
LIFBench: Evaluating the Instruction Following Performance and Stability of Large Language Models in Long-Context ScenariosLong
LIME: Less Is More for MLLM Evaluationfinding
LIST: Linearly Incremental SQL Translator for Single-Hop Reasoning, Generation and Verificationfinding
LLM Agents Making Agent ToolsLong
LLM Agents for Coordinating Multi-User Information Gatheringfinding
LLM Braces: Straightening Out LLM Predictions with Relevant Sub-UpdatesLong
LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedbackfinding
LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical StudyLong
LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encodingfinding
LLM as Entity Disambiguator for Biomedical Entity-LinkingShort
LLM as a Broken Telephone: Iterative Generation Distorts InformationLong
LLM-Based Multi-Agent Systems are Scalable Graph Generative Modelsfinding
LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detectionfinding
LLM-Enhanced Query Generation and Retrieval Preservation for Task-Oriented Dialoguefinding
LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputationfinding
LLM-Guided Semantic-Aware Clustering for Topic ModelingLong
LLM-Powered Test Case Generation for Detecting Bugs in Plausible ProgramsLong
LLM-Symbolic Integration for Robust Temporal Tabular Reasoningfinding
LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluationfinding
LLM-based Rumor Detection via Influence Guided Sample Selection and Game-based Perspective AnalysisLong
LLM-based Translation Inference with Iterative Bilingual Understandingfinding
LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Mediafinding
LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLMfinding
LLMs + Persona-Plug = Personalized LLMsLong
LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offlinefinding
LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Modelsfinding
LLMs Can Simulate Standardized Patients via Agent CoevolutionLong
LLMs Caught in the Crossfire: Malware Requests and Jailbreak ChallengesLong
LLMs Trust Humans More, That’s a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented GenerationLong
LLMs are Biased Evaluators But Not Biased for Fact-Centric Retrieval Augmented Generationfinding
LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Modelsfinding
LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English WritingLong
LLMs can be easily Confused by Instructional DistractionsLong
LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation TasksShort
LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution ShiftsLong
LLMs syntactically adapt their language use to their conversational partnerShort
LLM×MapReduce: Simplified Long-Sequence Processing using Large Language ModelsLong
LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech SynthesisLong
LLaMAs Have Feelings Too: Unveiling Sentiment and Emotion Representations in LLaMA Models Through ProbingLong
LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech EnhancementLong
LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-SteeringLong
LLäMmlein: Transparent, Compact and Competitive German-Only Language Models from ScratchLong
LPOI: Listwise Preference Optimization for Vision Language ModelsLong
LR²Bench: Evaluating Long-chain Reflective Reasoning Capabilities of Large Language Models via Constraint Satisfaction Problemsfinding
LSC-Eval: A General Framework to Evaluate Methods for Assessing Dimensions of Lexical Semantic Change Using LLM-Generated Synthetic Datafinding
LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace FusionLong
LTRAG: Enhancing Autoformalization and Self-refinement for Logical Reasoning with Thought-Guided RAGfinding
La Leaderboard: A Large Language Model Leaderboard for Spanish Varieties and Languages of Spain and Latin AmericaLong
LaTIM: Measuring Latent Token-to-Token Interactions in Mamba ModelsLong
Label-semantics Aware Generative Approach for Domain-Agnostic Multilabel Classificationfinding
LangMark: A Multilingual Dataset for Automatic Post-EditingLong
LangSAMP: Language-Script Aware Multilingual PretrainingLong
Language Constrained Multimodal Hyper Adapter For Many-to-Many Multimodal SummarizationLong
Language Fusion for Parameter-Efficient Cross-lingual TransferLong
Language Model Fine-Tuning on Scaled Survey Data for Predicting Distributions of Public OpinionsLong
Language Model Probabilities are Not Calibrated in Numeric ContextsLong
Language Models Grow Less Humanlike beyond Phase TransitionLong
Language Models Lack Temporal Generalization and Bigger is Not Betterfinding
Language Models Resist Alignment: Evidence From Data CompressionLong
Language Models can Subtly Deceive Without Lying: A Case Study on Strategic Phrasing in LegislationLong
Language Models, Graph Searching, and Supervision Adulteration: When More Supervision is Less and How to Make More MoreLong
Language Repository for Long Video Understandingfinding
Language-Codec: Bridging Discrete Codec Representations and Speech Language ModelsLong
Large Language Models Are Natural Video Popularity Predictorsfinding
Large Language Models Still Exhibit Bias in Long Textfinding
Large Language Models Struggle to Describe the Haystack without Human Help: A Social Science-Inspired Evaluation of Topic ModelsLong
Large Language Models are Good Relational LearnersLong
Large Language Models are Miscalibrated In-Context Learnersfinding
Large Language Models as Neurolinguistic Subjects: Discrepancy between Performance and Competencefinding
Large Language Models for Predictive Analysis: How Far Are They?finding
Large Language Models in Bioinformatics: A Surveyfinding
Large Language and Protein Assistant for Protein-Protein Interactions PredictionLong
Large Language and Reasoning Models are Shallow Disjunctive ReasonersLong
Large Margin Representation Learning for Robust Cross-lingual Named Entity RecognitionLong
Large Vocabulary Size Improves Large Language Modelsfinding
Latent Distribution Decouple for Uncertain-Aware Multimodal Multi-label Emotion Recognitionfinding
LazyReview: A Dataset for Uncovering Lazy Thinking in NLP Peer ReviewsLong
Learn to Memorize: Scalable Continual Learning in Semiparametric Models with Mixture-of-Neighbors Induction MemoryLong
Learning Auxiliary Tasks Improves Reference-Free Hallucination Detection in Open-Domain Long-Form GenerationShort
Learning First-Order Logic Rules for Argumentation MiningLong
Learning Sparsity for Effective and Efficient Music Performance Question AnsweringShort
Learning Task Representations from In-Context Learningfinding
Learning Together to Perform Better: Teaching Small-Scale LLMs to Collaborate via Preferential Rationale TuningLong
Learning from Committee: Reasoning Distillation from a Mixture of Teachers with Peer-Reviewfinding
Learning from Negative Samples in Biomedical Generative Entity Linkingfinding
Learning to Align Multi-Faceted Evaluation: A Unified and Robust Frameworkfinding
Learning to Generate Structured Output with Schema Reinforcement LearningLong
Learning to Insert [PAUSE] Tokens for Better Reasoningfinding
Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional AttentionLong
Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Gamesfinding
Learning to Reason Over Time: Timeline Self-Reflection for Improved Temporal Reasoning in Language ModelsLong
Learning to Reason from Feedback at Test-TimeLong
Learning to Rewrite: Generalized LLM-Generated Text DetectionLong
Learning to Select In-Context Demonstration Preferred by Large Language Modelfinding
LegalAgentBench: Evaluating LLM Agents in Legal DomainLong
LegalCore: A Dataset for Event Coreference Resolution in Legal Documentsfinding
LegalReasoner: Step-wised Verification-Correction for Legal Judgment ReasoningLong
LegoMT2: Selective Asynchronous Sharded Data Parallel Training for Massive Neural Machine Translationfinding
Lemmas Matter, But Not Like That: Predictors of Lemma-Based Generalization in Morphological Inflectionfinding
Lemmatisation & Morphological Analysis of Unedited Greek: Do Simple Tasks Need Complex Solutions?finding
Length Controlled Generation for Black-box LLMsLong
Length-Induced Embedding Collapse in PLM-based ModelsLong
Less Mature is More Adaptable for Sentence-level Language ModelingLong
Less for More: Enhanced Feedback-aligned Mixed LLMs for Molecule Caption Generation and Fine-Grained NLI EvaluationLong
Less is More: Explainable and Efficient ICD Code Prediction with Clinical EntitiesLong
Less, but Better: Efficient Multilingual Expansion for LLMs via Layer-wise Mixture-of-ExpertsLong
Let The Jury Decide: Fair Demonstration Selection for In-Context Learning through Incremental Greedy Evaluationfinding
Let’s Be Self-generated via Step by Step: A Curriculum Learning Approach to Automated Reasoning with Large Language Modelsfinding
Let’s Fuse Step by Step: A Generative Fusion Decoding Algorithm with LLMs for Robust and Instruction-Aware ASR and OCRfinding
Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI CollaborationLong
Leveraging Human Production-Interpretation Asymmetries to Test LLM Cognitive PlausibilityShort
Leveraging In-Context Learning for Political Bias Testing of LLMsLong
Leveraging LLMs for Bangla Grammar Error Correction: Error Categorization, Synthetic Data, and Model Evaluationfinding
Leveraging Large Language Models for Conversational Multi-Doc Question Answering: The First Place of WSDM Cup 2024finding
Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMsShort
Leveraging Unit Language Guidance to Advance Speech Modeling in Textless Speech-to-Speech Translationfinding
Leveraging Variation Theory in Counterfactual Data Augmentation for Optimized Active Learningfinding
LexCLiPR: Cross-Lingual Paragraph Retrieval from Legal JudgmentsLong
LexGen: Domain-aware Multilingual Lexicon GenerationLong
LexKeyPlan: Planning with Keyphrases and Retrieval Augmentation for Legal Text Generation: A Case Study on European Court of Human Rights CasesShort
LexTempus: Enhancing Temporal Generalizability of Legal Language Models Through Dynamic Mixture of ExpertsLong
Lexical Diversity-aware Relevance Assessment for Retrieval-Augmented GenerationLong
Lexical Recall or Logical Reasoning: Probing the Limits of Reasoning Abilities in Large Language ModelsLong
Libra: Leveraging Temporal Images for Biomedical Radiology Analysisfinding
Library-Like Behavior In Language Models is Enhanced by Self-Referencing Causal CyclesLong
Lifelong Model Editing with Graph-Based External Memoryfinding
Lightweight Query Checkpoint: Classifying Faulty User Queries to Mitigate Hallucinations in Large Language Model Question Answeringfinding
Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not ArgumentsLong
Limited-Resource Adapters Are Regularizers, Not LinguistsShort
Linguistic Generalizability of Test-Time Scaling in Mathematical ReasoningLong
Listen, Watch, and Learn to Feel: Retrieval-Augmented Emotion Reasoning for Compound Emotion Generationfinding
Listening to Patients: Detecting and Mitigating Patient Misreport in Medical Dialogue Systemfinding
Literary Evidence Retrieval via Long-Context Language ModelsShort
Literature Meets Data: A Synergistic Approach to Hypothesis GenerationLong
Llama See, Llama Do: A Mechanistic Perspective on Contextual Entrainment and Distraction in LLMsLong
LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMsLong
LlamaPIE: Proactive In-Ear Conversation Assistantsfinding
LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMsfinding
LoFTI: Localization and Factuality Transfer to Indian Localesfinding
LoGU: Long-form Generation with Uncertainty ExpressionsLong
LoRMA: Low-Rank Multiplicative Adaptation for LLMsfinding
LocAgent: Graph-Guided LLM Agents for Code LocalizationLong
Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Provingfinding
Localizing and Mitigating Errors in Long-form Question Answeringfinding
Locate-and-Focus: Enhancing Terminology Translation in Speech Language ModelsLong
Logic-Regularized Verifier Elicits Reasoning from LLMsLong
LogicGame: Benchmarking Rule-Based Reasoning Abilities of Large Language Modelsfinding
LogicPro: Improving Complex Logical Reasoning via Program-Guided LearningLong
Logical Consistency is Vital: Neural-Symbolic Information Retrieval for Negative-Constraint Queriesfinding
Logical DA: Enhancing Data Augmentation for Logical Reasoning via a Multi-Agent Systemfinding
Logical forms complement probability in understanding language model (and human) performanceLong
Long-form Hallucination Detection with Self-elicitationfinding
LongAttn: Selecting Long-context Training Data via Token-level Attentionfinding
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context MultitasksLong
LongCite: Enabling LLMs to Generate Fine-grained Citations in Long-Context QAfinding
LongDPO: Unlock Better Long-form Generation Abilities for LLMs via Critique-augmented Stepwise Informationfinding
LongDocURL: a Comprehensive Multimodal Long Document Benchmark Integrating Understanding, Reasoning, and LocatingLong
LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Datafinding
LongReD: Mitigating Short-Text Degradation of Long-Context Large Language Models via Restoration DistillationLong
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language ModelsLong
LongReward: Improving Long-context Large Language Models with AI FeedbackLong
LongSafety: Evaluating Long-Context Safety of Large Language ModelsLong
Look & Mark: Leveraging Radiologist Eye Fixations and Bounding boxes in Multimodal Large Language Models for Chest X-ray Report Generationfinding
Look Both Ways and No Sink: Converting LLMs into Text Encoders without TrainingLong
Lost in Literalism: How Supervised Training Shapes Translationese in LLMsLong
Lost in Multilinguality: Dissecting Cross-lingual Factual Inconsistency in Transformer Language ModelsLong
Lost in Transcription, Found in Distribution Shift: Demystifying Hallucination in Speech Foundation Modelsfinding
Lost in Translation: Benchmarking Commercial Machine Translation Models for Dyslexic-Style Textfinding
Lost in the Context: Insufficient and Distracted Attention to Contexts in Preference ModelingLong
Low-Bit Quantization Favors Undertrained LLMsLong
Low-Entropy Watermark Detection via Bayes’ Rule Derived Detectorfinding
Low-Rank Interconnected Adaptation across Layersfinding
Low-Resource Grammatical Error Correction: Selective Data Augmentation with Round-Trip Machine Translationfinding
Lunar Twins: We Choose to Go to the Moon with Large Language Modelsfinding
M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation EvaluationLong
M-RangeDetector: Enhancing Generalization in Machine-Generated Text Detection through Multi-Range Attention Masksfinding
M-RewardBench: Evaluating Reward Models in Multilingual SettingsLong
M2-TabFact: Multi-Document Multi-Modal Fact Verification with Visual and Textual Representations of Tabular Datafinding
M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive Theoryfinding
M2RC-EVAL: Massively Multilingual Repository-level Code Completion EvaluationLong
M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMsLong
M3HG: Multimodal, Multi-scale, and Multi-type Node Heterogeneous Graph for Emotion Cause Triplet Extraction in Conversationsfinding
MAGI: Multi-Agent Guided Interview for Psychiatric Assessmentfinding
MAGIC-VQA: Multimodal And Grounded Inference with Commonsense Knowledge for Visual Question Answeringfinding
MAGNET: Augmenting Generative Decoders with Representation Learning and Infilling CapabilitiesLong
MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented GenerationLong
MALAMUTE: A Multilingual, Highly-granular, Template-free, Education-based Probing Datasetfinding
MAM: Modular Multi-Agent Framework for Multi-Modal Medical Diagnosis via Role-Specialized Collaborationfinding
MANBench: Is Your Multimodal Model Smarter than Human?finding
MAPLE: Enhancing Review Generation with Multi-Aspect Prompt LEarning in Explainable RecommendationLong
MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation AlignmentLong
MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement LearningLong
MARK: Multi-agent Collaboration with Ranking Guidance for Text-attributed Graph Clusteringfinding
MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation DatasetLong
MATCHED: Multimodal Authorship-Attribution To Combat Human Trafficking in Escort-Advertisement Datafinding
MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at ScaleLong
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistencyfinding
MCS-Bench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in Chinese Classical StudiesLong
MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidancefinding
MDCure: A Scalable Pipeline for Multi-Document Instruction-FollowingLong
MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Modelsfinding
MECoT: Markov Emotional Chain-of-Thought for Personality-Consistent Role-Playingfinding
MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential DiagnosisLong
MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notesfinding
MEGen: Generative Backdoor into Large Language Models via Model Editingfinding
MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generationfinding
MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLPfinding
MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented GenerationLong
MEMIT-Merge: Addressing MEMIT’s Key-Value Conflicts in Same-Subject Batch Editing for LLMsfinding
MERIT: Multi-Agent Collaboration for Unsupervised Time Series Representation Learningfinding
METAL: A Multi-Agent Framework for Chart Generation with Test-Time ScalingLong
MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignmentfinding
MEXMA: Token-level objectives improve sentence representationsLong
MEraser: An Effective Fingerprint Erasure Approach for Large Language ModelsLong
MFinMeeting: A Multilingual, Multi-Sector, and Multi-Task Financial Meeting Understanding Evaluation Datasetfinding
MHALO: Evaluating MLLMs as Fine-grained Hallucination Detectorsfinding
MIG: Automatic Data Selection for Instruction Tuning by Maximizing Information Gain in Semantic Spacefinding
MIND: A Multi-agent Framework for Zero-shot Harmful Meme DetectionLong
MIR: Methodology Inspiration Retrieval for Scientific Research ProblemsLong
MIRAGE: Exploring How Large Language Models Perform in Complex Social Interactive EnvironmentsShort
MIRe: Enhancing Multimodal Queries Representation via Fusion-Free Modality Interaction for Multimodal Retrievalfinding
MISP-Meeting: A Real-World Dataset with Multimodal Cues for Long-form Meeting Transcription and SummarizationLong
MLAS-LoRA: Language-Aware Parameters Detection and LoRA-Based Knowledge Transfer for Multilingual Machine TranslationLong
MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenariosfinding
MM-R3: On (In-)Consistency of Vision-Language Models (VLMs)finding
MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought VerificationLong
MMBoundary: Advancing MLLM Knowledge Boundary Awareness through Reasoning Step Confidence CalibrationLong
MMDEND: Dendrite-Inspired Multi-Branch Multi-Compartment Parallel Spiking Neuron for Sequence ModelingLong
MMEvol: Empowering Multimodal Large Language Models with Evol-Instructfinding
MMInA: Benchmarking Multihop Multimodal Internet Agentsfinding
MMLU-CF: A Contamination-free Multi-task Language Understanding BenchmarkLong
MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding BenchmarkLong
MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World ConversationLong
MMRefine: Unveiling the Obstacles to Robust Refinement in Multimodal Large Language Modelsfinding
MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokensfinding
MMSciBench: Benchmarking Language Models on Chinese Multimodal Scientific Problemsfinding
MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Modelsfinding
MMXU: A Multi-Modal and Multi-X-ray Understanding Dataset for Disease Progressionfinding
MONTROSE: LLM-driven Monte Carlo Tree Search Self-Refinement for Cross-Domain Rumor Detectionfinding
MOSAIC: Multiple Observers Spotting AI Contentfinding
MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identificationfinding
MPL: Multiple Programming Languages with Large Language Models for Information Extractionfinding
MPO: Multilingual Safety Alignment via Reward Gap OptimizationLong
MPVStance: Mitigating Hallucinations in Stance Detection with Multi-Perspective VerificationLong
MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple TablesLong
MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teamingLong
MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answeringfinding
MUSE: A Multimodal Conversational Recommendation Dataset with Scenario-Grounded User Profilesfinding
MUSTS: MUltilingual Semantic Textual Similarity BenchmarkShort
MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matchingfinding
MVTamperBench: Evaluating Robustness of Vision-Language Modelsfinding
MWPO: Enhancing LLMs Performance through Multi-Weight Preference Strength and Length Optimizationfinding
MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine ProjectionLong
MaXIFE: Multilingual and Cross-lingual Instruction Following EvaluationLong
Machine Theory of Mind Needs Machine Validationfinding
Machine Translation Models are Zero-Shot Detectors of Translation Directionfinding
MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context InferenceLong
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph TranslationLong
Make Imagination Clearer! Stable Diffusion-based Visual Imagination for Multimodal Machine TranslationLong
Making FETCH! Happen: Finding Emergent Dog Whistles Through Common HabitatsLong
Making LLMs Better Many-to-Many Speech-to-Text Translators with Curriculum LearningLong
Making RALM Robust to Irrelevant Contexts via Layer Knowledge Guided Attentionfinding
Mamba Knockout for Unraveling Factual Information FlowLong
Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent SystemLong
Map&Make: Schema Guided Text to Table GenerationLong
MapNav: A Novel Memory Representation via Annotated Semantic Maps for VLM-based Vision-and-Language NavigationLong
Mapping 1,000+ Language Models via the Log-Likelihood VectorLong
Mapping the Podcast Ecosystem with the Structured Podcast Research CorpusLong
Marco-Bench-MIF: On Multilingual Instruction-Following Capability of Large LanguageLong
Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning ModelsLong
MasRouter: Learning to Route LLMs for Multi-Agent SystemsLong
Masking in Multi-hop QA: An Analysis of How Language Models Perform with Context PermutationLong
Masks Can be Learned as an Alternative to ExpertsLong
Massively Multilingual Instruction-Following Information Extractionfinding
Math Neurosurgery: Isolating Language Models’ Math Reasoning Abilities Using Only Forward PassesLong
MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoningfinding
MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction FusionLong
Matina: A Culturally-Aligned Persian Language Model Using Multiple LoRA Expertsfinding
Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal RetrievalLong
Maximizing the Effectiveness of Larger BERT Models for CompressionLong
Maximum Score Routing For Mixture-of-Expertsfinding
McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Modelsfinding
MeMoTune: A Measure and Moment-Driven Fine-Tuning Framework for Quantized Large Language Modelsfinding
Meaning Beyond Truth Conditions: Evaluating Discourse Level Understanding via Anaphora AccessibilityLong
Meaning Variation and Data Quality in the Corpus of Founding Era American EnglishShort
Measuring Bias and Agreement in Large Language Model Presupposition Judgmentsfinding
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable MetricLong
Measuring Social Biases in Masked Language Models by Proxy of Prediction QualityLong
Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalizationfinding
Measuring What Matters: Evaluating Ensemble LLMs with Label Refinement in Inductive Codingfinding
Measuring the Effect of Transcription Noise on Downstream Language Understanding TasksLong
Mechanistic Interpretability of Emotion Inference in Large Language Modelsfinding
MedCite: Can Language Models Generate Verifiable Text for Medicine?finding
Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented GenerationLong
MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPsfinding
MegaPairs: Massive Data Synthesis for Universal Multimodal RetrievalLong
MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agentsfinding
MemeDetoxNet: Balancing Toxicity Reduction and Context Preservationfinding
MemeQA: Holistic Evaluation for Meme UnderstandingLong
Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine TranslationShort
Memorization vs. Reasoning: Updating LLMs with New Knowledgefinding
Memorizing is Not Enough: Deep Knowledge Injection Through ReasoningLong
Memory or Reasoning? Explore How LLMs Compute Mixed Arithmetic Expressionsfinding
Memory-augmented Query Reconstruction for LLM-based Knowledge Graph Reasoningfinding
Merge Hijacking: Backdoor Attacks to Model Merging of Large Language ModelsLong
MergePrint: Merge-Resistant Fingerprints for Robust Black-box Ownership Verification of Large Language ModelsLong
Meta-Learning Neural Mechanisms rather than Bayesian PriorsLong
Meta-Reflection: A Feedback-Free Reflection Learning FrameworkLong
Meta-Tool: Unleash Open-World Function Calling Capabilities of General-Purpose Large Language ModelsLong
Meta-rater: A Multi-dimensional Data Selection Method for Pre-training Language ModelsLong
MetaSynth: Meta-Prompting-Driven Agentic Scaffolds for Diverse Synthetic Data Generationfinding
Metagent-P: A Neuro-Symbolic Planning Agent with Metacognition for Open Worldsfinding
Metaphor and Large Language Models: When Surface Features Matter More than Deep Understandingfinding
MiLiC-Eval: Benchmarking Multilingual LLMs for China’s Minority Languagesfinding
Micro-Act: Mitigate Knowledge Conflict in Question Answering via Actionable Self-ReasoningLong
Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMsLong
Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Modelsfinding
Mimicking the Familiar: Dynamic Command Generation for Information Theft Attacks in LLM Tool-Learning SystemLong
Mind Your Theory: Theory of Mind Goes Deeper Than Reasoningfinding
Mind the (Belief) Gap: Group Identity in the World of LLMsfinding
Mind the Gap: Static and Interactive Evaluations of Large Audio ModelsLong
Mind the Gesture: Evaluating AI Sensitivity to Culturally Offensive Non-Verbal GesturesLong
MindBridge: Scalable and Cross-Model Knowledge Editing via Memory-Augmented Modalityfinding
MindRef: Mimicking Human Memory for Hierarchical Reference Retrieval with Fine-Grained Location AwarenessShort
MiniELM: A Lightweight and Adaptive Query Rewriting Framework for E-Commerce Search Optimizationfinding
MiniKV: Pushing the Limits of 2-Bit KV Cache via Compression and System Co-Design for Efficient Long Context Inferencefinding
MiniLongBench: The Low-cost Long Context Understanding Benchmark for Large Language ModelsLong
Minimal Pair-Based Evaluation of Code-SwitchingLong
Mining Complex Patterns of Argumentative Reasoning in Natural Language DialogueLong
Mining the uncertainty patterns of humans and models in the annotation of moral foundations and human valuesLong
MinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMsfinding
Mis-prompt: Benchmarking Large Language Models for Proactive Error HandlingLong
Missing the Margins: A Systematic Literature Review on the Demographic Representativeness of LLMsfinding
Mitigate Position Bias in LLMs via Scaling a Single Hidden States Channelfinding
Mitigating Bias in RAG: Controlling the Embedderfinding
Mitigating Confounding in Speech-Based Dementia Detection through Weight MaskingLong
Mitigating Demonstration Bias through Global Coevolutionary Reasoningfinding
Mitigating Hallucination in Multimodal Large Language Model via Hallucination-targeted Direct Preference Optimizationfinding
Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question AnsweringLong
Mitigating Negative Interference in Multilingual Knowledge Editing through Null-Space Constraintsfinding
Mitigating Non-Representative Prototypes and Representation Bias in Few-Shot Continual Relation ExtractionLong
Mitigating Paraphrase Attacks on Machine-Text Detection via Paraphrase Inversionfinding
Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive DecodingShort
Mitigating Selection Bias with Node Pruning and Auxiliary OptionsLong
Mitigating Shortcut Learning with InterpoLated LearningLong
Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT ReasoningLong
Mixture of Decoding: An Attention-Inspired Adaptive Decoding Strategy to Mitigate Hallucinations in Large Vision-Language Modelsfinding
Mixture of Ordered Scoring Experts for Cross-prompt Essay Trait ScoringLong
Mixture of Small and Large Models for Chinese Spelling CheckLong
Mixture of Structural-and-Textual Retrieval over Text-rich Graph Knowledge Basesfinding
Mixture of insighTful Experts (MoTE): The Synergy of Reasoning Chains and Expert Mixtures in Self-AlignmentLong
Mixture-of-Personas Language Models for Population Simulationfinding
Mixtures of In-Context LearnersLong
MlingConf: A Comprehensive Study of Multilingual Confidence Estimation on Large Language Modelsfinding
MoC: Mixtures of Text Chunking Learners for Retrieval-Augmented Generation SystemLong
MoQAE: Mixed-Precision Quantization for Long-Context LLM Inference via Mixture of Quantization-Aware ExpertsLong
MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learningfinding
MobiLoRA: Accelerating LoRA-based LLM Inference on Mobile Devices via Context-aware KV Cache OptimizationLong
MockConf: A Student Interpretation Dataset: Analysis, Word- and Span-level Alignment and BaselinesLong
Modal Dependency Parsing via Biaffine Attention with Self-Loopfinding
Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language ModelsLong
Model Extrapolation Expedites AlignmentLong
Model Performance-Guided Evaluation Data Selection for Effective Prompt Optimizationfinding
Model-Dependent Moderation: Inconsistencies in Hate Speech Detection Across LLM-based Systemsfinding
Modeling Complex Semantics Relation with Contrastively Fine-Tuned Relational EncodersLong
Modeling Uncertainty in Composed Image Retrieval via Probabilistic EmbeddingsLong
Modeling the Evolution of English Noun Compounds with Feature-Rich Diachronic Compositionality PredictionLong
Moderation Matters: Measuring Conversational Moderation Impact in English as a Second Language Group Discussionfinding
Modular Sentence Encoders: Separating Language Specialization from Cross-Lingual AlignmentLong
MolRAG: Unlocking the Power of Large Language Models for Molecular Property PredictionLong
Monitoring Decoding: Mitigating Hallucination via Evaluating the Factuality of Partial Response during Generationfinding
More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting ObjectivesLong
MorphMark: Flexible Adaptive Watermarking for Large Language ModelsLong
Mosaic-IT: Cost-Free Compositional Data Synthesis for Instruction Tuningfinding
MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?finding
Movie101v2: Improved Movie Narration BenchmarkLong
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive TrainingLong
Multi-Agent Collaboration via Cross-Team Orchestrationfinding
Multi-Attribute Steering of Language Models via Targeted InterventionLong
Multi-Facet Blending for Faceted Query-by-Example RetrievalLong
Multi-Hop Question Generation via Dual-Perspective Keyword Guidancefinding
Multi-Hop Reasoning for Question Answering with Hyperbolic Representationsfinding
Multi-Level Explanations for Generative Language ModelsLong
Multi-Modality Expansion and Retention for LLMs through Parameter Merging and DecouplingLong
Multi-Prompting Decoder Helps Better Language Understandingfinding
Multi-Sense Embeddings for Language Models and Knowledge Distillationfinding
Multi-document Summarization through Multi-document Event Relation Graph Reasoning in LLMs: a case study in Framing Bias MitigationLong
Multi-level Association Refinement Network for Dialogue Aspect-based Sentiment Quadruple AnalysisLong
Multi-level Relevance Document Identifier Learning for Generative RetrievalLong
Multi-matrix Factorization Attentionfinding
Multi-perspective Alignment for Increasing Naturalness in Neural Machine TranslationLong
Multi-task Adversarial Attacks against Black-box Model with Few-shot QueriesLong
Multi-word Measures: Modeling Semantic Change in Compound Nounsfinding
MultiAgentBench : Evaluating the Collaboration and Competition of LLM agentsLong
MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMsfinding
MultiHoax: A Dataset of Multi-hop False-premise questionsfinding
MultiMSD: A Corpus for Multilingual Medical Text Simplification from Online Medical Referencesfinding
MultiSocial: Multilingual Benchmark of Machine-Generated Text Detection of Social-Media TextsLong
MultiTEND: A Multilingual Benchmark for Natural Language to NoSQL Query Translationfinding
Multilingual Arbitration: Optimizing Data Pools to Accelerate Multilingual ProgressLong
Multilingual Definition Modelingfinding
Multilingual Encoder Knows more than You Realize: Shared Weights Pretraining for Extremely Low-Resource LanguagesLong
Multilingual Gloss-free Sign Language Translation: Towards Building a Sign Language Foundation ModelShort
Multilingual Retrieval Augmented Generation for Culturally-Sensitive Tasks: A Benchmark for Cross-lingual Robustnessfinding
Multilingual Text-to-Image Generation Magnifies Gender StereotypesLong
Multimodal Causal Reasoning Benchmark: Challenging Multimodal Large Language Models to Discern Causal Links Across Modalitiesfinding
Multimodal Coreference Resolution for Chinese Social Media Dialogues: Dataset and Benchmark ApproachLong
Multimodal Fusion and Coherence Modeling for Video Topic Segmentationfinding
Multimodal Inconsistency Reasoning (MMIR): A New Benchmark for Multimodal Reasoning Modelsfinding
Multimodal Invariant Sentiment Representation Learningfinding
Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Reviewfinding
Multimodal Machine Translation with Text-Image In-depth Questioningfinding
Multimodal Pragmatic Jailbreak on Text-to-image ModelsLong
Multimodal Transformers are Hierarchical Modal-wise Heterogeneous GraphsLong
Multiple LLM Agents Debate for Equitable Cultural AlignmentLong
MutantPrompt: Prompt Optimization via Mutation Under a Budget on Modest-sized LMsfinding
Mutual-Taught for Co-adapting Policy and Reward ModelsLong
My Words Imply Your Opinion: Reader Agent-Based Propagation Enhancement for Personalized Implicit Emotion AnalysisLong
M³GQA: A Multi-Entity Multi-Hop Multi-Setting Graph Question Answering BenchmarkLong
NBDESCRIB: A Dataset for Text Description Generation from Tables and Code in Jupyter Notebooks with Guidelinesfinding
NGQA: A Nutritional Graph Question Answering Benchmark for Personalized Health-aware Nutritional ReasoningLong
NOVA: An Iterative Planning Framework for Enhancing Scientific Innovation with Large Language Modelsfinding
NarGINA: Towards Accurate and Interpretable Children’s Narrative Ability Assessment via Narrative Graphsfinding
Narrative Media Framing in Political Discoursefinding
NativQA: Multilingual Culturally-Aligned Natural Query for LLMsfinding
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionLong
Natural Language Processing in Support of Evidence-based Medicine: A Scoping Reviewfinding
Natural Language Reasoning in Large Language Models: Analysis and Evaluationfinding
Natural Logic at the Core: Dynamic Rewards for Entailment Tree Generationfinding
NavRAG: Generating User Demand Instructions for Embodied Navigation through Retrieval-Augmented LLMfinding
Navigating Rifts in Human-LLM Grounding: Study and BenchmarkLong
Navigating the Political Compass: Evaluating Multilingual LLMs across Languages and Nationalitiesfinding
NegVQA: Can Vision Language Models Understand Negation?finding
Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text EmbeddingsLong
Nemotron-CC: Transforming Common Crawl into a Refined Long-Horizon Pretraining DatasetLong
NeoQA: Evidence-based Question Answering with Generated News Eventsfinding
Nested-Refinement Metamorphosis: Reflective Evolution for Efficient Optimization of Networking Problemsfinding
NetSafe: Exploring the Topological Safety of Multi-agent Systemfinding
NeuSym-RAG: Hybrid Neural Symbolic Retrieval with Multiview Structuring for PDF Question AnsweringLong
Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language ModelsLong
Neural Parameter Search for Slimmer Fine-Tuned Models and Better TransferLong
Neural Topic Modeling with Large Language Models in the LoopLong
Neuro-Symbolic Query Compilerfinding
Neuron Activation Modulation for Text Style Transfer: Guiding Large Language Modelsfinding
Neuron Empirical Gradient: Discovering and Quantifying Neurons’ Global Linear ControllabilityLong
Neuron-Level Sequential Editing for Large Language ModelsLong
NeuronMerge: Merging Models via Functional Neuron Groupsfinding
Neutralizing Bias in LLM Reasoning using Entailment Graphsfinding
NewsInterview: a Dataset and a Playground to Evaluate LLMs’ Grounding Gap via Informational InterviewsLong
NexusSum: Hierarchical LLM Agents for Long-Form Narrative SummarizationLong
No Questions are Stupid, but some are Poorly Posed: Understanding Poorly-Posed Information-Seeking QuestionsLong
None of the Above, Less of the Right Parallel Patterns in Human and LLM Performance on Multi-Choice Questions Answeringfinding
NorEval: A Norwegian Language Understanding and Generation Evaluation Benchmarkfinding
Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attributions ExplainabilityLong
Not All Terms Matter: Recall-Oriented Adaptive Learning for PLM-aided Query Expansion in Open-Domain Question AnsweringLong
Not quite Sherlock Holmes: Language model predictions do not reliably differentiate impossible from improbable eventsfinding
NovelCR: A Large-Scale Bilingual Dataset Tailored for Long-Span Coreference Resolutionfinding
Nuclear Deployed!: Analyzing Catastrophic Risks in Decision-making of Autonomous LLM Agentsfinding
Nudging: Inference-time Alignment of LLMs via Guided DecodingLong
Nunchi-Bench: Benchmarking Language Models on Cultural Reasoning with a Focus on Korean Superstitionfinding
NusaAksara: A Multimodal and Multilingual Benchmark for Preserving Indonesian Indigenous ScriptsLong
OASIS: Order-Augmented Strategy for Improved Code SearchLong
ODDA: An OODA-Driven Diverse Data Augmentation Framework for Low-Resource Relation Extractionfinding
OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal RetrievalLong
ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended CapabilitiesLong
ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Studyfinding
OS Agents: A Survey on MLLM-based Agents for Computer, Phone and Browser UseLong
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task SynthesisLong
OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agentsfinding
OZSpeech: One-step Zero-shot Speech Synthesis with Learned-Prior-Conditioned Flow MatchingLong
ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion AttacksLong
Odysseus Navigates the Sirens’ Song: Dynamic Focus Decoding for Factual and Diverse Open-Ended Text GenerationLong
Offline Reinforcement Learning for LLM Multi-step Reasoningfinding
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human PreferenceLong
OmniCharacter: Towards Immersive Role-Playing Agents with Seamless Speech-Language Personality InteractionLong
OmniFlatten: An End-to-end GPT Model for Seamless Voice ConversationLong
On Entity Identification in Language Modelsfinding
On Generalization across Measurement Systems: LLMs Entail More Test-Time Compute for Underrepresented CulturesLong
On Many-Shot In-Context Learning for Long-Context EvaluationLong
On Support Samples of Next Word PredictionLong
On Synthesizing Data for Context Attribution in Question AnsweringLong
On Synthetic Data Strategies for Domain-Specific Generative RetrievalLong
On the Acquisition of Shared Grammatical Representations in Bilingual Language ModelsLong
On the Consistency of Commonsense in Large Language Modelsfinding
On the Generalization vs Fidelity Paradox in Knowledge Distillationfinding
On the Limit of Language Models as Planning FormalizersLong

ACL accepted papers in other years

ACL 2024 (1,930)ACL 2023 (2,052)ACL 2022 (1,031)ACL 2021 (710)

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