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

On the Mutual Influence of Gender and Occupation in LLM RepresentationsLong
On the Relation Between Fine-Tuning, Topological Properties, and Task Performance in Sense-Enhanced EmbeddingsLong
On the Reliability of Large Language Models for Causal DiscoveryLong
On the Risk of Evidence Pollution for Malicious Social Text Detection in the Era of LLMsLong
On the Robust Approximation of ASR Metricsfinding
On the Role of Semantic Proto-roles in Semantic Analysis: What do LLMs know about agency?finding
On-Policy Self-Alignment with Fine-grained Knowledge Feedback for Hallucination Mitigationfinding
One QuantLLM for ALL: Fine-tuning Quantized LLMs Once for Efficient DeploymentsLong
One for All: Update Parameterized Knowledge Across Multiple Models with Once EditLong
One-Dimensional Object Detection for Streaming Text Segmentation of Meeting Dialoguefinding
One-for-All Pruning: A Universal Model for Customized Compression of Large Language Modelsfinding
Online Iterative Self-Alignment for Radiology Report GenerationLong
Only a Little to the Left: A Theory-grounded Measure of Political Bias in Large Language ModelsLong
Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question AnsweringLong
Open-Set Living Need Prediction with Large Language Modelsfinding
Open-World Attribute Mining for E-Commerce Products with Multimodal Self-Correction Instruction TuningLong
Open-World Authorship Attributionfinding
Open-World Planning via Lifted Regression with LLM-Inferred Affordances for Embodied AgentsLong
OpenCoder: The Open Cookbook for Top-Tier Code Large Language ModelsLong
OpenHuEval: Evaluating Large Language Model on Hungarian Specificsfinding
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and OptimizationLong
Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal TransportLong
Optima: Optimizing Effectiveness and Efficiency for LLM-Based Multi-Agent Systemfinding
Optimal Transport-Based Token Weighting scheme for Enhanced Preference OptimizationLong
Optimized Text Embedding Models and Benchmarks for Amharic Passage Retrievalfinding
Optimizing Decomposition for Optimal Claim VerificationLong
Optimizing Multi-Hop Document Retrieval Through Intermediate Representationsfinding
Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert ModelsLong
Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question AnsweringLong
Optimizing Reasoning for Text-to-SQL with Execution Feedbackfinding
Order Matters: Investigate the Position Bias in Multi-constraint Instruction Followingfinding
Out-of-Distribution Detection via LLM-Guided Outlier Generation for Text-attributed Graphfinding
Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language ModelsLong
Outlier-weighed Layerwise Sampling for LLM Fine-tuningfinding
P-CoT: A Pedagogically-motivated Participatory Chain-of-Thought Prompting for Phonological Reasoning in LLMsfinding
P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Expertsfinding
P2 Law: Scaling Law for Post-Training After Model PruningLong
P3: Prompts Promote Promptingfinding
PAM: Paraphrase AMR-Centric Evaluation Metricfinding
PAP2PAT: Benchmarking Outline-Guided Long-Text Patent Generation with Patent-Paper Pairsfinding
PARME: Parallel Corpora for Low-Resourced Middle Eastern LanguagesLong
PARSQL: Enhancing Text-to-SQL through SQL Parsing and Reasoningfinding
PASTEL : Polarity-Aware Sentiment Triplet Extraction with LLM-as-a-Judgefinding
PCoT: Persuasion-Augmented Chain of Thought for Detecting Fake News and Social Media DisinformationLong
PECAN: LLM-Guided Dynamic Progress Control with Attention-Guided Hierarchical Weighted Graph for Long-Document QAfinding
PEToolLLM: Towards Personalized Tool Learning in Large Language Modelsfinding
PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowchartsfinding
PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference Optimizationfinding
PIC: Unlocking Long-Form Text Generation Capabilities of Large Language Models via Position ID CompressionLong
PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context OptimizationLong
PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for FreeLong
PIPER: Benchmarking and Prompting Event Reasoning Boundary of LLMs via Debiasing-Distillation Enhanced TuningLong
PISCO: Pretty Simple Compression for Retrieval-Augmented Generationfinding
PKAG-DDI: Pairwise Knowledge-Augmented Language Model for Drug-Drug Interaction Event Text GenerationLong
PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human PreferenceLong
PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Playfinding
PM3-KIE: A Probabilistic Multi-Task Meta-Model for Document Key Information Extractionfinding
PPT: A Minor Language News Recommendation Model via Cross-Lingual Preference Pattern TransferLong
PQR: Improving Dense Retrieval via Potential Query ModelingLong
PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-EncoderLong
PRMBench: A Fine-grained and Challenging Benchmark for Process-Level Reward ModelsLong
PROMTEC: Fast LLM Inference Decoding using Prompt Multi-Lookup with Template Database and Common Sequencesfinding
PROPER: A Progressive Learning Framework for Personalized Large Language Models with Group-Level AdaptationLong
PTQ1.61: Push the Real Limit of Extremely Low-Bit Post-Training Quantization Methods for Large Language ModelsLong
PVP: An Image Dataset for Personalized Visual Persuasion with Persuasion Strategies, Viewer Characteristics, and Persuasiveness RatingsLong
PaSa: An LLM Agent for Comprehensive Academic Paper SearchLong
Packing Analysis: Packing Is More Appropriate for Large Models or Datasets in Supervised Fine-tuningfinding
Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMsLong
Pandora’s Box or Aladdin’s Lamp: A Comprehensive Analysis Revealing the Role of RAG Noise in Large Language ModelsLong
Parameter-Aware Contrastive Knowledge Editing: Tracing and Rectifying based on Critical Transmission PathsLong
Parameter-Efficient Fine-Tuning via Circular Convolutionfinding
Parenting: Optimizing Knowledge Selection of Retrieval-Augmented Language Models with Parameter Decoupling and Tailored TuningLong
Partial Colexifications Improve Concept EmbeddingsLong
Past Meets Present: Creating Historical Analogy with Large Language ModelsLong
Pattern Recognition or Medical Knowledge? The Problem with Multiple-Choice Questions in MedicineLong
Patterns Over Principles: The Fragility of Inductive Reasoning in LLMs under Noisy Observationsfinding
People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated textLong
PerSphere: A Comprehensive Framework for Multi-Faceted Perspective Retrieval and SummarizationLong
Performance Gap in Entity Knowledge Extraction Across Modalities in Vision Language ModelsLong
Persistent Homology of Topic Networks for the Prediction of Reader CuriosityLong
Persona Dynamics: Unveiling the Impact of Persona Traits on Agents in Text-Based GamesLong
Persona-judge: Personalized Alignment of Large Language Models via Token-level Self-judgmentfinding
PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Datafinding
PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistantsfinding
PersonaX: A Recommendation Agent-Oriented User Modeling Framework for Long Behavior Sequencefinding
Personal Travel Solver: A Preference-Driven LLM-Solver System for Travel PlanningLong
Personality-Guided Code Generation Using Large Language ModelsLong
Personalized Generation In Large Model Era: A SurveyLong
Personalized Text Generation with Contrastive Activation SteeringLong
Perspective Transition of Large Language Models for Solving Subjective Tasksfinding
Phonotomizer: A Compact, Unsupervised, Online Training Approach to Real-Time, Multilingual Phonetic SegmentationLong
PhysReason: A Comprehensive Benchmark towards Physics-Based ReasoningLong
Physics: Benchmarking Foundation Models on University-Level Physics Problem Solvingfinding
PipeSpec: Breaking Stage Dependencies in Hierarchical LLM Decodingfinding
Pitfalls of Scale: Investigating the Inverse Task of Redefinition in Large Language Modelsfinding
Pixel-Level Reasoning Segmentation via Multi-turn ConversationsLong
PlanGenLLMs: A Modern Survey of LLM Planning CapabilitiesLong
Planning with Diffusion Models for Target-Oriented Dialogue SystemsLong
Planning-Driven Programming: A Large Language Model Programming WorkflowLong
PlanningArena: A Modular Benchmark for Multidimensional Evaluation of Planning and Tool LearningLong
Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language ModelsLong
PodAgent: A Comprehensive Framework for Podcast Generationfinding
Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in KoreanLong
PolyNarrative: A Multilingual, Multilabel, Multi-domain Dataset for Narrative Extraction from News ArticlesLong
Ponder & Press: Advancing Visual GUI Agent towards General Computer Controlfinding
PopAlign: Diversifying Contrasting Patterns for a More Comprehensive AlignmentLong
Position Paper: MeMo: Towards Language Models with Associative Memory Mechanismsfinding
Position-Aware Depth Decay Decoding (D3): Boosting Large Language Model Inference Efficiencyfinding
Position-aware Automatic Circuit DiscoveryLong
Positional Overload: Positional Debiasing and Context Window Extension for Large Language Models using Set EncodingLong
Powerformer: Efficient and High-Accuracy Privacy-Preserving Language Model with Homomorphic EncryptionLong
Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation CriteriaLong
Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and ChallengesLong
Pre-Training Curriculum for Multi-Token Prediction in Language ModelsLong
Pre-training Distillation for Large Language Models: A Design Space ExplorationLong
Pre3: Enabling Deterministic Pushdown Automata for Faster Structured LLM GenerationLong
PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR AccuracyLong
PreSumm: Predicting Summarization Performance Without Summarizingfinding
Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddingsfinding
PredictaBoard: Benchmarking LLM Score Predictabilityfinding
Predicting Depression in Screening Interviews from Interactive Multi-Theme Collaborationfinding
Predicting Implicit Arguments in Procedural Video InstructionsLong
Predicting Through Generation: Why Generation Is Better for PredictionLong
Predicting Turn-Taking and Backchannel in Human-Machine Conversations Using Linguistic, Acoustic, and Visual SignalsLong
Prediction Hubs are Context-Informed Frequent Tokens in LLMsLong
Prediction-Augmented Generation for Automatic Diagnosis Tasksfinding
Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Datafinding
Pretraining Context Compressor for Large Language Models with Embedding-Based MemoryLong
Principled Content Selection to Generate Diverse and Personalized Multi-Document SummariesLong
Principled Understanding of Generalization for Generative Transformer Models in Arithmetic Reasoning TasksLong
PrivaCI-Bench: Evaluating Privacy with Contextual Integrity and Legal ComplianceLong
Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Trainingfinding
PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and RestorationLong
Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language ModelsLong
ProBench: Judging Multimodal Foundation Models on Open-ended Multi-domain Expert Tasksfinding
ProMALex: Progressive Modular Adapters for Multi-Jurisdictional Legal Language ModelingLong
ProMedTS: A Self-Supervised, Prompt-Guided Multimodal Approach for Integrating Medical Text and Time Seriesfinding
ProMind-LLM: Proactive Mental Health Care via Causal Reasoning with Sensor Datafinding
Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Modelsfinding
Probability-Consistent Preference Optimization for Enhanced LLM Reasoningfinding
Probing LLMs for Multilingual Discourse Generalization Through a Unified Label SetLong
Probing Relative Interaction and Dynamic Calibration in Multi-modal Entity AlignmentLong
Probing Subphonemes in Morphology Modelsfinding
Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasksfinding
Problem-Solving Logic Guided Curriculum In-Context Learning for LLMs Complex Reasoningfinding
Process-based Self-Rewarding Language Modelsfinding
ProcessBench: Identifying Process Errors in Mathematical ReasoningLong
ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformationsfinding
Profiling News Media for Factuality and Bias Using LLMs and the Fact-Checking Methodology of Human Expertsfinding
ProgCo: Program Helps Self-Correction of Large Language ModelsShort
Program Synthesis Benchmark for Visual Programming in XLogoOnline EnvironmentLong
Programming by Example meets Historical Linguistics: A Large Language Model Based Approach to Sound Law InductionLong
Progressive LoRA for Multimodal Continual Instruction Tuningfinding
Progressive Multimodal Reasoning via Active RetrievalLong
ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generationfinding
Prompt Candidates, then Distill: A Teacher-Student Framework for LLM-driven Data AnnotationLong
Prompt-Guided Internal States for Hallucination Detection of Large Language ModelsLong
PromptCoT: Synthesizing Olympiad-level Problems for Mathematical Reasoning in Large Language Modelsfinding
PromptWizard: Optimizing Prompts via Task-Aware, Feedback-Driven Self-Evolutionfinding
Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agentsfinding
ProtoLens: Advancing Prototype Learning for Fine-Grained Interpretability in Text ClassificationLong
ProvBench: A Benchmark of Legal Provision Recommendation for Contract Auto-ReviewingLong
Proverbs Run in Pairs: Evaluating Proverb Translation Capability of Large Language Modelfinding
ProxAnn: Use-Oriented Evaluations of Topic Models and Document ClusteringLong
Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete DataLong
PruneVid: Visual Token Pruning for Efficient Video Large Language Modelsfinding
Pruning General Large Language Models into Customized Expert Modelsfinding
PsyAdvisor: A Plug-and-Play Strategy Advice Planner with Proactive Questioning in Psychological ConversationsLong
PsyDT: Using LLMs to Construct the Digital Twin of Psychological Counselor with Personalized Counseling Style for Psychological CounselingLong
PsyDial: A Large-scale Long-term Conversational Dataset for Mental Health SupportLong
PunchBench: Benchmarking MLLMs in Multimodal Punchline ComprehensionLong
PwnGPT: Automatic Exploit Generation Based on Large Language ModelsLong
P²Net: Parallel Pointer-based Network for Key Information Extraction with Complex Layoutsfinding
Q-Mamba: Towards more efficient Mamba models via post-training quantizationfinding
Q-STRUM Debate: Query-Driven Contrastive Summarization for Recommendation Comparisonfinding
QAEncoder: Towards Aligned Representation Learning in Question Answering SystemsLong
QAEval: Mixture of Evaluators for Question-Answering Task EvaluationLong
QDTSynth: Quality-Driven Formal Theorem Synthesis for Enhancing Proving Performance of LLMsLong
QG-SMS: Enhancing Test Item Analysis via Student Modeling and SimulationLong
QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question AnsweringLong
QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithmfinding
Qorǵau: Evaluating Safety in Kazakh-Russian Bilingual Contextsfinding
QuASAR: A Question-Driven Structure-Aware Approach for Table-to-Text GenerationLong
Quaff: Quantized Parameter-Efficient Fine-Tuning under Outlier Spatial Stability HypothesisLong
QualiSpeech: A Speech Quality Assessment Dataset with Natural Language Reasoning and DescriptionsLong
Quantification of Large Language Model DistillationLong
Quantifying Lexical Semantic Shift via Unbalanced Optimal TransportLong
Quantifying Misattribution Unfairness in Authorship AttributionShort
Quantifying Semantic Emergence in Language ModelsLong
Quantile Regression with Large Language Models for Price Predictionfinding
Quantized Can Still Be Calibrated: A Unified Framework to Calibration in Quantized Large Language ModelsLong
Query-Driven Multimodal GraphRAG: Dynamic Local Knowledge Graph Construction for Online Reasoningfinding
Query-driven Document-level Scientific Evidence Extraction from Biomedical StudiesLong
QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Languagefinding
Question Answering in Climate Adaptation for Agriculture: Model Development and Evaluation with Expert Feedbackfinding
Question-Aware Knowledge Graph Prompting for Enhancing Large Language Modelsfinding
Qwen2.5-xCoder: Multi-Agent Collaboration for Multilingual Code Instruction TuningLong
R-Fairness: Assessing Fairness of Ranking in Subjective DataLong
R-VLM: Region-Aware Vision Language Model for Precise GUI Groundingfinding
R.R.: Unveiling LLM Training Privacy through Recollection and Rankingfinding
R2-MultiOmnia: Leading Multilingual Multimodal Reasoning via Self-TrainingLong
R2D2: Remembering, Replaying and Dynamic Decision Making with a Reflective Agentic MemoryLong
R3Mem: Bridging Memory Retention and Retrieval via Reversible Compressionfinding
RADAR: Enhancing Radiology Report Generation with Supplementary Knowledge InjectionLong
RAEmoLLM: Retrieval Augmented LLMs for Cross-Domain Misinformation Detection Using In-Context Learning Based on Emotional InformationLong
RAG-Critic: Leveraging Automated Critic-Guided Agentic Workflow for Retrieval Augmented GenerationLong
RAG-RewardBench: Benchmarking Reward Models in Retrieval Augmented Generation for Preference Alignmentfinding
RAGEval: Scenario Specific RAG Evaluation Dataset Generation FrameworkLong
RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discoveryfinding
RARE: Retrieval-Augmented Reasoning Enhancement for Large Language ModelsLong
RASD: Retrieval-Augmented Speculative Decodingfinding
RASPberry: Retrieval-Augmented Monte Carlo Tree Self-Play with Reasoning Consistency for Multi-Hop Question Answeringfinding
RATE-Nav: Region-Aware Termination Enhancement for Zero-shot Object Navigation with Vision-Language Modelsfinding
RATIONALYST: Pre-training Process-Supervision for Improving ReasoningLong
READoc: A Unified Benchmark for Realistic Document Structured Extractionfinding
REAL-MM-RAG: A Real-World Multi-Modal Retrieval BenchmarkLong
REALM: A Dataset of Real-World LLM Use Casesfinding
REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?finding
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Spacefinding
RISE: Reasoning Enhancement via Iterative Self-Exploration in Multi-hop Question Answeringfinding
RL-Guider: Leveraging Historical Decisions and Feedback for Drug Editing with Large Language Modelsfinding
RLKGF: Reinforcement Learning from Knowledge Graph Feedback Without Human Annotationsfinding
RMoA: Optimizing Mixture-of-Agents through Diversity Maximization and Residual Compensationfinding
RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented GenerationLong
RQT: Hierarchical Residual Quantization for Multi-Model Compressionfinding
RSCF: Relation-Semantics Consistent Filter for Entity Embedding of Knowledge GraphLong
RSVP: Reasoning Segmentation via Visual Prompting and Multi-modal Chain-of-ThoughtLong
RTADev: Intention Aligned Multi-Agent Framework for Software Developmentfinding
RUBY: An Effective Framework for Multi-Constraint Multi-Hop Question GenerationLong
RaaS: Reasoning-Aware Attention Sparsity for Efficient LLM Reasoningfinding
Random Splitting Negatively Impacts NER Evaluation: Quantifying and Eliminating the Overestimation of NER Performancefinding
Rank, Chunk and Expand: Lineage-Oriented Reasoning for Taxonomy Expansionfinding
RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-ThoughtsLong
Ranked Voting based Self-Consistency of Large Language Modelsfinding
Ranking Unraveled: Recipes for LLM Rankings in Head-to-Head AI CombatLong
Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliabilityfinding
Rationalize and Align: Enhancing Writing Assistance with Rationale via Self-Training for Improved Alignmentfinding
Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectivesfinding
Re-identification of De-identified Documents with Autoregressive InfillingLong
Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media PlatformsLong
Re3Syn: A Dependency-Based Data Synthesis Framework for Long-Context Post-trainingLong
ReKG-MCTS: Reinforcing LLM Reasoning on Knowledge Graphs via Training-Free Monte Carlo Tree Searchfinding
ReLearn: Unlearning via Learning for Large Language ModelsLong
RePanda: Pandas-powered Tabular Verification and ReasoningLong
ReSCORE: Label-free Iterative Retriever Training for Multi-hop Question Answering with Relevance-Consistency SupervisionLong
Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar BooksLong
Real-time Factuality Assessment from Adversarial FeedbackLong
RealHiTBench: A Comprehensive Realistic Hierarchical Table Benchmark for Evaluating LLM-Based Table Analysisfinding
Reason from Future: Reverse Thought Chain Enhances LLM Reasoningfinding
ReasonerRank: Redefining Language Model Evaluation with Ground-Truth-Free Ranking Frameworksfinding
Reasoning Circuits in Language Models: A Mechanistic Interpretation of Syllogistic Inferencefinding
Reasoning Does Not Necessarily Improve Role-Playing Abilityfinding
Reasoning is All You Need for Video Generalization: A Counterfactual Benchmark with Sub-question Evaluationfinding
Reasoning with Graphs: Structuring Implicit Knowledge to Enhance LLMs Reasoningfinding
RecLM: Recommendation Instruction TuningLong
Recent Advances in Speech Language Models: A SurveyLong
Reconsidering LLM Uncertainty Estimation Methods in the WildLong
RecordTwin: Towards Creating Safe Synthetic Clinical Corporafinding
Rectifying Belief Space via Unlearning to Harness LLMs’ Reasoningfinding
Recurrent Knowledge Identification and Fusion for Language Model Continual LearningLong
Recursive Question Understanding for Complex Question Answering over Heterogeneous Personal Datafinding
Red Queen: Exposing Latent Multi-Turn Risks in Large Language Modelsfinding
Red-Teaming LLM Multi-Agent Systems via Communication Attacksfinding
Redundancy Principles for MLLMs BenchmarksLong
Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddingsfinding
RedundancyLens: Revealing and Exploiting Visual Token Processing Redundancy for Efficient Decoder-Only MLLMsfinding
Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Modelsfinding
Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language ModelsLong
Refining Salience-Aware Sparse Fine-Tuning Strategies for Language ModelsLong
Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Modelsfinding
ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical AgentsLong
ReflectDiffu: Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion FrameworkLong
ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflectionfinding
Reflection on Knowledge Graph for Large Language Models Reasoningfinding
ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code GenerationLong
RefreshKV: Updating Small KV Cache During Long-form GenerationLong
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal TrainingLong
Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine TranslationLong
Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Modelsfinding
Reinforced IR: A Self-Boosting Framework For Domain-Adapted Information RetrievalLong
Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contextsfinding
RelEdit: Evaluating Conceptual Knowledge Editing in Language Models via Relational Reasoningfinding
RelationalCoder: Rethinking Complex Tables via Programmatic Relational TransformationLong
Relevance Scores Calibration for Ranked List Truncation via TMP Adapterfinding
Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?finding
Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal PredictionLong
RemoteRAG: A Privacy-Preserving LLM Cloud RAG Servicefinding
Removal of Hallucination on Hallucination: Debate-Augmented RAGLong
Removing Prompt-template Bias in Reinforcement Learning from Human Feedbackfinding
Representation Bending for Large Language Model SafetyLong
Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and AttitudesLong
Reranking-based Generation for Unbiased Perspective Summarizationfinding
Research Borderlands: Analysing Writing Across Research CulturesLong
Research Community Perspectives on “Intelligence” and Large Language Modelsfinding
Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answeringfinding
Response Wide Shut? Surprising Observations in Basic Vision Language Model CapabilitiesLong
Rethinking Diverse Human Preference Learning through Principal Component Analysisfinding
Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?Short
Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web CorporaShort
Rethinking Prompt-based Debiasing in Large Language Modelfinding
Rethinking Repetition Problems of LLMs in Code GenerationLong
Rethinking Reward Model Evaluation Through the Lens of Reward OveroptimizationLong
Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic HintsShort
Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challengesfinding
Rethinking Table Instruction Tuningfinding
Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability TheoryLong
Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Modelsfinding
Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Modelsfinding
Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program GenerationLong
Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoningfinding
Retrieve to Explain: Evidence-driven Predictions for Explainable Drug Target IdentificationLong
RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within GenerationLong
Retrofitting Large Language Models with Dynamic TokenizationLong
Retrospective Learning from InteractionsLong
Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processingfinding
Revealing and Mitigating the Local Pattern Shortcuts of Mambafinding
Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial EditingLong
Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-upLong
Reverse Preference Optimization for Complex Instruction Followingfinding
Review-Instruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Modelsfinding
Revisit Self-Debugging with Self-Generated Tests for Code GenerationLong
Revisiting 3D LLM Benchmarks: Are We Really Testing 3D Capabilities?finding
Revisiting Classical Chinese Event Extraction with Ancient Literature InformationLong
Revisiting Common Assumptions about Arabic Dialects in NLPLong
Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following AbilityLong
Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty?Short
Revisiting In-Context Learning with Long Context Language Modelsfinding
Revisiting LLMs as Zero-Shot Time Series Forecasters: Small Noise Can Break Large ModelsShort
Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helpsfinding
Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training StrategiesLong
Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregationfinding
Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias ResultsShort
Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KLfinding
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?Long
Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document RestorationLong
Reward Generalization in RLHF: A Topological Perspectivefinding
Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instructionfinding
Rhetorical Device-Aware Sarcasm Detection with Counterfactual Data Augmentationfinding
Rhythm Controllable and Efficient Zero-Shot Voice Conversion via Shortcut Flow MatchingLong
RiOT: Efficient Prompt Refinement with Residual Optimization TreeLong
Right Answer, Wrong Score: Uncovering the Inconsistencies of LLM Evaluation in Multiple-Choice Question Answeringfinding
RoCoFT: Efficient Finetuning of Large Language Models with Row-Column UpdatesLong
RoToR: Towards More Reliable Responses for Order-Invariant InputsLong
Robust Data Watermarking in Language Models by Injecting Fictitious Knowledgefinding
Robust Estimation of Population-Level Effects in Repeated-Measures NLP Experimental DesignsLong
Robust Preference Optimization via Dynamic Target Marginsfinding
Robust Utility-Preserving Text Anonymization Based on Large Language ModelsLong
Robust and Minimally Invasive Watermarking for EaaSfinding
Robustness and Confounders in the Demographic Alignment of LLMs with Human Perceptions of Offensivenessfinding
RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Followingfinding
RolePlot: A Systematic Framework for Evaluating and Enhancing the Plot-Progression Capabilities of Role-Playing AgentsLong
Rolling the DICE on Idiomaticity: How LLMs Fail to Grasp ContextLong
RomanLens: The Role Of Latent Romanization In Multilinguality In LLMsfinding
Root Defense Strategies: Ensuring Safety of LLM at the Decoding LevelLong
RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimizationfinding
Rubrik’s Cube: Testing a New Rubric for Evaluating Explanations on the CUBE datasetLong
RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World ScenariosLong
RuleEdit: Towards Rule-Level Knowledge Generalization to Mitigate Over-Editing in Large Language Modelsfinding
S-RAG: A Novel Audit Framework for Detecting Unauthorized Use of Personal Data in RAG SystemsLong
S2R: Teaching LLMs to Self-verify and Self-correct via Reinforcement LearningLong
S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic ModelingLong
S3 - Semantic Signal SeparationLong
SAKE: Steering Activations for Knowledge EditingLong
SAM Decoding: Speculative Decoding via Suffix AutomatonLong
SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models’ Knowledge of Indian Culturefinding
SARA: Salience-Aware Reinforced Adaptive Decoding for Large Language Models in Abstractive SummarizationLong
SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkagefinding
SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human InterventionLong
SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language ModelsLong
SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Typesfinding
SCOP: Evaluating the Comprehension Process of Large Language Models from a Cognitive ViewLong
SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotationfinding
SCOPE: Optimizing Key-Value Cache Compression in Long-context GenerationLong
SCULPT: Systematic Tuning of Long PromptsLong
SConU: Selective Conformal Uncertainty in Large Language ModelsLong
SDBench: A Survey-based Domain-specific LLM Benchmarking and Optimization FrameworkLong
SDD: Self-Degraded Defense against Malicious Fine-tuningLong
SDPO: Segment-Level Direct Preference Optimization for Social AgentsLong
SEA-HELM: Southeast Asian Holistic Evaluation of Language Modelsfinding
SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic EmbeddingsLong
SEAL: Scaling to Emphasize Attention for Long-Context RetrievalLong
SECRET: Semi-supervised Clinical Trial Document Similarity SearchLong
SEE: Continual Fine-tuning with Sequential Ensemble of Expertsfinding
SEE: Strategic Exploration and Exploitation for Cohesive In-Context Prompt OptimizationLong
SEK: Self-Explained Keywords Empower Large Language Models for Code Generationfinding
SELF-PERCEPT: Introspection Improves Large Language Models’ Detection of Multi-Person Mental Manipulation in ConversationsShort
SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event DetectionLong
SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?Long
SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignmentfinding
SGIC: A Self-Guided Iterative Calibration Framework for RAGLong
SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQLLong
SHARE: Shared Memory-Aware Open-Domain Long-Term Dialogue Dataset Constructed from Movie ScriptLong
SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMsfinding
SHuBERT: Self-Supervised Sign Language Representation Learning via Multi-Stream Cluster PredictionLong
SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-TuningLong
SIKeD: Self-guided Iterative Knowledge Distillation for Mathematical Reasoningfinding
SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor DetectionLong
SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage Trainingfinding
SMART: Self-Aware Agent for Tool Overuse Mitigationfinding
SOTOPIA-Ω: Dynamic Strategy Injection Learning and Social Instruction Following Evaluation for Social AgentsLong
SPECTRA: Faster Large Language Model Inference with Optimized Internal and External SpeculationLong
SPHERE: An Evaluation Card for Human-AI Systemsfinding
SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical EvaluationLong
SPICA: Retrieving Scenarios for Pluralistic In-Context Alignmentfinding
SPILL: Domain-Adaptive Intent Clustering based on Selection and Pooling with Large Language Modelsfinding
SPOT: Zero-Shot Semantic Parsing Over Property Graphsfinding
SQL Injection Jailbreak: A Structural Disaster of Large Language Modelsfinding
SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMsfinding
SR-LLM: Rethinking the Structured Representation in Large Language ModelLong
STARS: A Unified Framework for Singing Transcription, Alignment, and Refined Style Annotationfinding
STATE ToxiCN: A Benchmark for Span-level Target-Aware Toxicity Extraction in Chinese Hate Speech Detectionfinding
STEM-POM: Evaluating Language Models Math-Symbol Reasoning in Document Parsingfinding
STORM-BORN: A Challenging Mathematical Derivations Dataset Curated via a Human-in-the-Loop Multi-Agent Frameworkfinding
STORYTELLER: An Enhanced Plot-Planning Framework for Coherent and Cohesive Story Generationfinding
STRICTA: Structured Reasoning in Critical Text Assessment for Peer Review and BeyondLong
STUN: Structured-Then-Unstructured Pruning for Scalable MoE PruningLong
STaR-SQL: Self-Taught Reasoner for Text-to-SQLLong
STeCa: Step-level Trajectory Calibration for LLM Agent Learningfinding
SURVEYFORGE : On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey WritingLong
SWE-Dev: Building Software Engineering Agents with Training and Inference Scalingfinding
SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolutionfinding
SYNTHIA: Novel Concept Design with Affordance CompositionLong
SYNTHVERIFY: Enhancing Zero-Shot Claim Verification through Step-by-Step Synthetic Data Generationfinding
Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal VerificationLong
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilitiesfinding
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearningfinding
SafeLawBench: Towards Safe Alignment of Large Language Modelsfinding
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language ModelLong
SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Modelsfinding
Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detectionfinding
Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to ArtifactsLong
Safety Alignment via Constrained Knowledge UnlearningLong
Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safetyfinding
Same Company, Same Signal: The Role of Identity in Earnings Call Transcriptsfinding
Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy CompetitionLong
Sampling-based Pseudo-Likelihood for Membership Inference Attacksfinding
Sandcastles in the Storm: Revisiting the (Im)possibility of Strong WatermarkingLong
ScEdit: Script-based Assessment of Knowledge Editingfinding
Scalable Vision Language Model Training via High Quality Data CurationLong
ScaleBiO: Scalable Bilevel Optimization for LLM Data ReweightingLong
Scaling LLMs’ Social Reasoning: Sprinkle Cognitive “Aha Moment” into Fundamental Long-thought Logical Capabilitiesfinding
Scaling Laws and Efficient Inference for Ternary Language ModelsLong
Scaling Laws for Multilingual Language Modelsfinding
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data GenerationLong
Scaling up the State Size of RNN LLMs for Long-Context ScenariosLong
ScanEZ: Integrating Cognitive Models with Self-Supervised Learning for Spatiotemporal Scanpath PredictionShort
SceneGenAgent: Precise Industrial Scene Generation with Coding AgentLong
SceneGram: Conceptualizing and Describing Tangrams in Scene Contextfinding
Sci-LoRA: Mixture of Scientific LoRAs for Cross-Domain Lay Paraphrasingfinding
SciVer: Evaluating Foundation Models for Multimodal Scientific Claim VerificationLong
SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problemsfinding
SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented GenerationLong
Search-in-Context: Efficient Multi-Hop QA over Long Contexts via Monte Carlo Tree Search with Dynamic KV Retrievalfinding
Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary ExpansionLong
See the World, Discover Knowledge: A Chinese Factuality Evaluation for Large Vision Language Modelsfinding
SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed ScienceLong
Seeing What Tastes Good: Revisiting Multimodal Distributional Semantics in the Billion Parameter Erafinding
Seeking Rational Demonstrations for Large Language Models: A Domain Generalization Approach to Unsupervised Cross-Domain Keyphrase GenerationShort
Segment First or Comprehend First? Explore the Limit of Unsupervised Word Segmentation with Large Language ModelsLong
Segment-Based Attention Masking for GPTsLong
Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language ModelsLong
Select, Read, and Write: A Multi-Agent Framework of Full-Text-based Related Work Generationfinding
SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Modelsfinding
Selecting Demonstrations for Many-Shot In-Context Learning via Gradient Matchingfinding
Selecting and Merging: Towards Adaptable and Scalable Named Entity Recognition with Large Language ModelsLong
Self-Correction is More than Refinement: A Learning Framework for Visual and Language Reasoning Tasksfinding
Self-Critique Guided Iterative Reasoning for Multi-hop Question Answeringfinding
Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical ReasoningLong
Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveationfinding
Self-Improvement Towards Pareto Optimality: Mitigating Preference Conflicts in Multi-Objective Alignmentfinding
Self-Instructed Derived Prompt Generation Meets In-Context Learning: Unlocking New Potential of Black-Box LLMsLong
Self-Reasoning Language Models: Unfold Hidden Reasoning Chains with Few Reasoning Catalystfinding
Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generationfinding
Self-Steering Optimization: Autonomous Preference Optimization for Large Language Modelsfinding
Self-Taught Agentic Long Context UnderstandingLong
Self-Training Elicits Concise Reasoning in Large Language Modelsfinding
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teachingfinding
Self-attention-based Graph-of-Thought for Math Problem Solvingfinding
Self-play through Computational Runtimes improves Chart Reasoningfinding
Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language ModelsLong
SelfElicit: Your Language Model Secretly Knows Where is the Relevant EvidenceLong
Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual Transferfinding
Semantic Evaluation of Multilingual Data-to-Text Generation via NLI Fine-Tuning: Precision, Recall and F1 scoresfinding
Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language ModelsLong
Semantic Topology: a New Perspective for Communication Style Characterizationfinding
Semantic-Eval : A Semantic Comprehension Evaluation Framework for Large Language Models Generation without TrainingLong
SemanticCamo: Jailbreaking Large Language Models through Semantic Camouflagefinding
Semantics-aware prompting for translating NOtices To AirMenfinding
Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Modelsfinding
Sentimental Image Generation for Aspect-based Sentiment Analysisfinding
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Modelsfinding
Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in TransformersLong
SeqMMR: Sequential Model Merging and LLM Routing for Enhanced Batched Sequential Knowledge Editingfinding
SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translationfinding
Serial Lifelong Editing via Mixture of Knowledge ExpertsLong
Serial Position Effects of Large Language Modelsfinding
Shadow-Activated Backdoor Attacks on Multimodal Large Language Modelsfinding
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language ModelsLong
Sharper and Faster mean Better: Towards More Efficient Vision-Language Model for Hour-scale Long Video UnderstandingLong
Sheep’s Skin, Wolf’s Deeds: Are LLMs Ready for Metaphorical Implicit Hate Speech?Long
ShieldHead: Decoding-time Safeguard for Large Language Modelsfinding
ShifCon: Enhancing Non-Dominant Language Capabilities with a Shift-based Multilingual Contrastive FrameworkLong
Shifting from Ranking to Set Selection for Retrieval Augmented GenerationLong
ShortGPT: Layers in Large Language Models are More Redundant Than You Expectfinding
Should I Believe in What Medical AI Says? A Chinese Benchmark for Medication Based on Knowledge and ReasoningShort
Should I Trust You? Detecting Deception in Negotiations using Counterfactual RLfinding
Sightation Counts: Leveraging Sighted User Feedback in Building a BLV-aligned Dataset of Diagram DescriptionsLong
Sign2Vis: Automated Data Visualization from Sign Languagefinding
SignAlignLM: Integrating Multimodal Sign Language Processing into Large Language Modelsfinding
SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scalefinding
Silencing Empowerment, Allowing Bigotry: Auditing the Moderation of Hate Speech on TwitchLong
SimGRAG: Leveraging Similar Subgraphs for Knowledge Graphs Driven Retrieval-Augmented Generationfinding
SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech TranslationLong
Single-to-mix Modality Alignment with Multimodal Large Language Model for Document Image Machine TranslationLong
Sinhala Encoder-only Language Models and EvaluationLong
SkillAggregation: Reference-free LLM-Dependent AggregationLong
SkillVerse : Assessing and Enhancing LLMs with Tree EvaluationLong
SkyLLM: Cross-LLM-APIs Federation for Cost-effective Query Processingfinding
Slamming: Training a Speech Language Model on One GPU in a Dayfinding
Sleepless Nights, Sugary Days: Creating Synthetic Users with Health Conditions for Realistic Coaching Agent Interactionsfinding
Sliding Windows Are Not the End: Exploring Full Ranking with Long-Context Large Language ModelsLong
Small Changes, Big Impact: How Manipulating a Few Neurons Can Drastically Alter LLM AggressionLong
Small Encoders Can Rival Large Decoders in Detecting Groundednessfinding
Small Models Struggle to Learn from Strong Reasonersfinding
Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and InferenceLong
Smarter, Not Harder: Training-Free Adaptive Computation for Transformersfinding
Smotrom tvoja på ander drogoj verden! Resurrecting Dead Pidgin with Generative Models: Russenorsk Case Studyfinding
SoRFT: Issue Resolving with Subtask-oriented Reinforced Fine-TuningLong
Social Bias Benchmark for Generation: A Comparison of Generation and QA-Based Evaluationsfinding
SocialCC: Interactive Evaluation for Cultural Competence in Language AgentsLong
SocialEval: Evaluating Social Intelligence of Large Language ModelsLong
Socratic Style Chain-of-Thoughts Help LLMs to be a Better Reasonerfinding
SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMsLong
SongComposer: A Large Language Model for Lyric and Melody Generation in Song CompositionLong
Soundwave: Less is More for Speech-Text Alignment in LLMsLong
SpaRE: Enhancing Spatial Reasoning in Vision-Language Models with Synthetic DataLong
Span-based Semantic Role Labeling as Lexicalized Constituency Tree Parsingfinding
Sparse Latents Steer Retrieval-Augmented GenerationLong
Sparse Logit Sampling: Accelerating Knowledge Distillation in LLMsLong
Sparse Rewards Can Self-Train Dialogue Agentsfinding
Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMsShort
Spatial Coordinates as a Cell Language: A Multi-Sentence Framework for Imaging Mass Cytometry Analysisfinding
Speaking Beyond Language: A Large-Scale Multimodal Dataset for Learning Nonverbal Cues from Video-Grounded DialoguesLong
Spectral Insights into Data-Oblivious Critical Layers in Large Language Modelsfinding
Speculative Sampling via Exponential Racesfinding
Speech Act Patterns for Improving Generalizability of Explainable Politeness Detection Modelsfinding
SpeechFake: A Large-Scale Multilingual Speech Deepfake Dataset Incorporating Cutting-Edge Generation MethodsLong
SpeechIQ: Speech-Agentic Intelligence Quotient Across Cognitive Levels in Voice Understanding by Large Language ModelsLong
SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Informationfinding
Speed Up Your Code: Progressive Code Acceleration Through Bidirectional Tree EditingLong
SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep LayersLong
Splintering Nonconcatenative Languages for Better Tokenizationfinding
Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generationfinding
Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language ModelsShort
Squeezed Attention: Accelerating Long Context Length LLM InferenceLong
StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIsfinding
Standard Quality Criteria Derived from Current NLP Evaluations for Guiding Evaluation Design and Grounding Comparability and AI Compliance Assessmentsfinding
State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space ModelsShort
Statement-Tuning Enables Efficient Cross-lingual Generalization in Encoder-only Modelsfinding
Statistical Deficiency for Task Inclusion EstimationLong
Statistical inference on black-box generative models in the data kernel perspective spacefinding
Stealing Training Data from Large Language Models in Decentralized Training through Activation Inversion AttackLong
Steering into New Embedding Spaces: Analyzing Cross-Lingual Alignment Induced by Model Interventions in Multilingual Language ModelsLong
Steering off Course: Reliability Challenges in Steering Language ModelsLong
Step-by-Step Mastery: Enhancing Soft Constraint Following Ability of Large Language Modelsfinding
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Modelsfinding
Stepwise Reasoning Disruption Attack of LLMsLong
Stereotype Detection as a Catalyst for Enhanced Bias Detection: A Multi-Task Learning Approachfinding
Stereotype or Personalization? User Identity Biases Chatbot Recommendationsfinding
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding ModelsLong
StitchLLM: Serving LLMs, One Block at a TimeLong
Stochastic Chameleons: Irrelevant Context Hallucinations Reveal Class-Based (Mis)Generalization in LLMsLong
Stories that (are) Move(d by) Markets: A Causal Exploration of Market Shocks and Semantic Shifts across Different Partisan Groupsfinding
Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasksfinding
Stress-testing Machine Generated Text Detection: Shifting Language Models Writing Style to Fool Detectorsfinding
StrucText-Eval: Evaluating Large Language Model’s Reasoning Ability in Structure-Rich TextLong
StructFact: Reasoning Factual Knowledge from Structured Data with Large Language Modelsfinding
StructFlowBench: A Structured Flow Benchmark for Multi-turn Instruction Followingfinding
Structural Deep Encoding for Table Question Answeringfinding
Structural Reasoning Improves Molecular Understanding of LLMLong
Structure-adaptive Adversarial Contrastive Learning for Multi-Domain Fake News Detectionfinding
Structure-aware Domain Knowledge Injection for Large Language ModelsLong
Structured Discourse Representation for Factual Consistency Verificationfinding
Structured Pruning for Diverse Best-of-N Reasoning Optimizationfinding
SuLoRA: Subspace Low-Rank Adaptation for Parameter-Efficient Fine-Tuningfinding
SubLIME: Subset Selection via Rank Correlation Prediction for Data-Efficient LLM EvaluationLong
Substance over Style: Evaluating Proactive Conversational Coaching AgentsLong
Subtle Errors in Reasoning: Preference Learning via Error-injected Self-editingLong
Subword models struggle with word learning, but surprisal hides itShort
SudoLM: Learning Access Control of Parametric Knowledge with Authorization AlignmentLong
Summary Factual Inconsistency Detection Based on LLMs Enhanced by Universal Information Extractionfinding
Supervised Optimism Correction: Be Confident When LLMs Are Surefinding
Supervised and Unsupervised Probing of Shortcut Learning: Case Study on the Emergence and Evolution of Syntactic Heuristics in BERTfinding
SurveyPilot: an Agentic Framework for Automated Human Opinion Collection from Social MediaLong
SwiLTra-Bench: The Swiss Legal Translation BenchmarkLong
Symmetrical Visual Contrastive Optimization: Aligning Vision-Language Models with Minimal Contrastive ImagesLong
SynFix: Dependency-Aware Program Repair via RelationGraph Analysisfinding
SynGraph: A Dynamic Graph-LLM Synthesis Framework for Sparse Streaming User Sentiment Modelingfinding
SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge RefinementShort
SynapticRAG: Enhancing Temporal Memory Retrieval in Large Language Models through Synaptic Mechanismsfinding
Synergistic Augmentation: Enhancing Cross-Domain Zero-Shot Slot Filling with Small Model-Assisted Large Language Modelsfinding
Synergistic Weak-Strong Collaboration by Aligning PreferencesLong
Synergizing LLMs with Global Label Propagation for Multimodal Fake News DetectionLong
Synergizing Unsupervised Episode Detection with LLMs for Large-Scale News EventsLong
Syntactic Control of Language Models by Posterior Inferencefinding
SynthesizeMe! Inducing Persona-Guided Prompts for Personalized Reward Models in LLMsLong
Synthesizing Post-Training Data for LLMs through Multi-Agent SimulationLong
System Prompt Hijacking via Permutation Triggers in LLM Supply Chainsfinding
Systematic Evaluation of Auto-Encoding and Large Language Model Representations for Capturing Author States and Traitsfinding
Systematic Generalization in Language Models Scales with Information Entropyfinding
T-REG: Preference Optimization with Token-Level Reward RegularizationLong
T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI FeedbackLong
T2DR: A Two-Tier Deficiency-Resistant Framework for Incomplete Multimodal Learningfinding
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive ConceptsLong
T5Score: A Methodology for Automatically Assessing the Quality of LLM Generated Multi-Document Topic Setsfinding
TABGEN-ICL: Residual-Aware In-Context Example Selection for Tabular Data Generationfinding
TACLR: A Scalable and Efficient Retrieval-based Method for Industrial Product Attribute Value IdentificationLong
TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learningfinding
TAMP: Token-Adaptive Layerwise Pruning in Multimodal Large Language Modelsfinding
TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured DataLong
TC-Bench: Benchmarking Temporal Compositionality in Conditional Video Generationfinding
TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesisfinding
TC–RAG: Turing–Complete RAG’s Case study on Medical LLM SystemsLong
TDCSA: LLM-Guided Top-Down Approach for Robust Citation Sentiment Analysisfinding
TEACH: A Contrastive Knowledge Adaptive Distillation Framework for Classical Chinese UnderstandingLong
TESS 2: A Large-Scale Generalist Diffusion Language ModelLong
TETRIS: Optimal Draft Token Selection for Batch Speculative DecodingLong
THOR-MoE: Hierarchical Task-Guided and Context-Responsive Routing for Neural Machine TranslationLong
TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-JudgeLong
TRANS-ZERO: Self-Play Incentivizes Large Language Models for Multilingual Translation Without Parallel Datafinding
TRATES: Trait-Specific Rubric-Assisted Cross-Prompt Essay Scoringfinding
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data SynthesisLong
TROVE: A Challenge for Fine-Grained Text Provenance via Source Sentence Tracing and Relationship ClassificationLong
TReMu: Towards Neuro-Symbolic Temporal Reasoning for LLM-Agents with Memory in Multi-Session Dialoguesfinding
TST: A Schema-Based Top-Down and Dynamic-Aware Agent of Text-to-Table TasksLong
TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuningfinding
TUMLU: A Unified and Native Language Understanding Benchmark for Turkic LanguagesLong
TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic VideosLong
TWIST: Text-encoder Weight-editing for Inserting Secret Trojans in Text-to-Image ModelsLong
TabXEval: Why this is a Bad Table? An eXhaustive Rubric for Table Evaluationfinding
Table-Critic: A Multi-Agent Framework for Collaborative Criticism and Refinement in Table ReasoningLong
TableDreamer: Progressive and Weakness-guided Data Synthesis from Scratch for Table Instruction Tuningfinding
TableLLM: Enabling Tabular Data Manipulation by LLMs in Real Office Usage Scenariosfinding
TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language ModelsLong
Tag-Evol: Achieving Efficient Instruction Evolving via Tag Injectionfinding
Tag-Instruct: Controlled Instruction Complexity Enhancement through Structure-based Augmentationfinding
TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasksfinding
TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimizationfinding
Takin-VC: Expressive Zero-Shot Voice Conversion via Adaptive Hybrid Content Encoding and Enhanced Timbre ModelingLong
Talking Point based Ideological Discourse Analysis in News Eventsfinding
Taming LLMs with Gradient GroupingLong
Taming Language Models for Text-attributed Graph Learning with Decoupled AggregationLong
Targeted Syntactic Evaluation for Grammatical Error CorrectionLong
Task Calibration: Calibrating Large Language Models on Inference Tasksfinding
Task Facet Learning: A Structured Approach To Prompt Optimizationfinding
Task Knowledge Injection via Interpolations and Reinstatement for Large Language Model Generalizationfinding
Task-Informed Anti-Curriculum by Masking Improves Downstream Performance on Textfinding
Task-Oriented Automatic Fact-Checking with Frame-Semanticsfinding
Task-Specific Information Decomposition for End-to-End Dense Video CaptioningLong
TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research CorporaLong
Taxonomizing Representational Harms using Speech Act Theoryfinding
Taxonomy-Driven Knowledge Graph Construction for Domain-Specific Scientific Applicationsfinding
TeRDy: Temporal Relation Dynamics through Frequency Decomposition for Temporal Knowledge Graph CompletionLong
Teaching Text Agents to Learn Sequential Decision Making from FailureLong
Teaching Vision-Language Models to Ask: Resolving Ambiguity in Visual QuestionsLong
Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled PreferencesLong
TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and CompetitionLong
TechniqueRAG: Retrieval Augmented Generation for Adversarial Technique Annotation in Cyber Threat Intelligence Textfinding
Tell Me What You Don’t Know: Enhancing Refusal Capabilities of Role-Playing Agents via Representation Space Analysis and Editingfinding
Tell, Don’t Show: Leveraging Language Models’ Abstractive Retellings to Model Literary Themesfinding
Temporal Relation Extraction in Clinical Texts: A Span-based Graph Transformer ApproachLong
Temporal reasoning for timeline summarisation in social mediaLong
TestAgent: An Adaptive and Intelligent Expert for Human Assessmentfinding
TestNUC: Enhancing Test-Time Computing Approaches and Scaling through Neighboring Unlabeled Data ConsistencyLong
Text is All You Need: LLM-enhanced Incremental Social Event DetectionLong
Text-to-ES Bench: A Comprehensive Benchmark for Converting Natural Language to Elasticsearch QueryLong
Text2World: Benchmarking Large Language Models for Symbolic World Model Generationfinding
Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answeringfinding
That doesn’t sound right: Evaluating speech transcription quality in field linguistics corporaShort
That is Unacceptable: the Moral Foundations of CancelingLong
The AI Gap: How Socioeconomic Status Affects Language Technology InteractionsLong
The Alternative Annotator Test for LLM-as-a-Judge: How to Statistically Justify Replacing Human Annotators with LLMsLong
The Anatomy of Evidence: An Investigation Into Explainable ICD Codingfinding
The Behavior Gap: Evaluating Zero-shot LLM Agents in Complex Task-Oriented Dialogsfinding
The Cross-linguistic Role of Animacy in Grammar StructuresLong
The Devil Is in the Word Alignment Details: On Translation-Based Cross-Lingual Transfer for Token Classification Tasksfinding
The Distracting Effect: Understanding Irrelevant Passages in RAGLong
The Effectiveness of Uncased Tokeniziaion for Clinical Notesfinding
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early ExitLong
The Elephant in the Room: Exploring the Role of Neutral Words in Language Model Group-Agnostic Debiasingfinding
The Esethu Framework: Reimagining Sustainable Dataset Governance and Curation for Low-Resource LanguagesLong
The Essence of Contextual Understanding in Theory of Mind: A Study on Question Answering with Story CharactersLong
The Harmonic Structure of Information ContoursLong
The Hidden Attention of Mamba ModelsLong
The Impact of Auxiliary Patient Data on Automated Chest X-Ray Report Generation and How to Incorporate ItLong
The Impact of Large Language Models in Academia: from Writing to Speakingfinding
The Impact of Name Age Perception on Job Recommendations in LLMsfinding
The Impact of Token Granularity on the Predictive Power of Language Model SurprisalLong
The Impossibility of Fair LLMsLong
The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakagefinding
The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code GenerationLong
The Knowledge Microscope: Features as Better Analytical Lenses than NeuronsLong
The Law of Knowledge Overshadowing: Towards Understanding, Predicting and Preventing LLM Hallucinationfinding
The Lawyer That Never Thinks: Consistency and Fairness as Keys to Reliable AILong
The Lessons of Developing Process Reward Models in Mathematical Reasoningfinding
The Lies Characters Tell: Utilizing Large Language Models to Normalize Adversarial Unicode Perturbationsfinding
The Linguistic Connectivities Within Large Language Modelsfinding
The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual SubjectsLong
The Million Authors Corpus: A Cross-Lingual and Cross-Domain Wikipedia Dataset for Authorship Verificationfinding
The Mirage of Model Editing: Revisiting Evaluation in the WildLong
The Nature of NLP: Analyzing Contributions in NLP PapersLong
The Noisy Path from Source to Citation: Measuring How Scholars Engage with Past ResearchLong
The Reader is the Metric: How Textual Features and Reader Profiles Explain Conflicting Evaluations of AI Creative Writingfinding
The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Directionfinding
The Right Time Matters: Data Arrangement Affects Zero-Shot Generalization in Instruction Tuningfinding
The Rise of Darkness: Safety-Utility Trade-Offs in Role-Playing Dialogue Agentsfinding
The Role of Abstract Representations and Observed Preferences in the Ordering of Binomials in Large Language ModelsShort
The Role of Deductive and Inductive Reasoning in Large Language ModelsLong
The Role of Visual Modality in Multimodal Mathematical Reasoning: Challenges and InsightsLong
The Rotary Position Embedding May Cause Dimension Inefficiency in Attention Heads for Long-Distance Retrievalfinding
The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?finding
The Silent Saboteur: Imperceptible Adversarial Attacks against Black-Box Retrieval-Augmented Generation Systemsfinding
The Structural Safety Generalization Problemfinding
The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMsLong
The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM AgentsLong
The Threat of PROMPTS in Large Language Models: A System and User Prompt Perspectivefinding
The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language ModelsLong
The Two Paradigms of LLM Detection: Authorship Attribution vs. Authorship Verificationfinding
The UD-NewsCrawl Treebank: Reflections and Challenges from a Large-scale Tagalog Syntactic Annotation ProjectLong
The time scale of redundancy between prosody and linguistic contextLong
Theorem Prover as a Judge for Synthetic Data GenerationLong
TheoremExplainAgent: Towards Video-based Multimodal Explanations for LLM Theorem UnderstandingLong
Theoretical Analysis of Hierarchical Language Recognition and Generation by Transformers without Positional EncodingLong
Theoretical Guarantees for Minimum Bayes Risk DecodingLong
Theory of Mind in Large Language Models: Assessment and EnhancementLong
There’s No Such Thing as Simple Reasoning for LLMsfinding
They want to pretend not to understand: The Limits of Current LLMs in Interpreting Implicit Content of Political Discoursefinding
Think Both Ways: Teacher-Student Bidirectional Reasoning Enhances MCQ Generation and Distractor Qualityfinding
Think More, Hallucinate Less: Mitigating Hallucinations via Dual Process of Fast and Slow Thinkingfinding
Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward ModelingLong
ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrailsfinding
Thinking Before Running! Efficient Code Generation with Thorough Exploration and Optimal Refinementfinding
TiC-LM: A Web-Scale Benchmark for Time-Continual LLM PretrainingLong
TicTac: Time-aware Supervised Fine-tuning for Automatic Text Datingfinding
TigerLLM - A Family of Bangla Large Language ModelsShort
Time Course MechInterp: Analyzing the Evolution of Components and Knowledge in Large Language Modelsfinding
Time Travel: A Comprehensive Benchmark to Evaluate LMMs on Historical and Cultural Artifactsfinding
Time-MQA: Time Series Multi-Task Question Answering with Context EnhancementLong
TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarkingfinding
To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximizationfinding
TokAlign: Efficient Vocabulary Adaptation via Token AlignmentLong
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMsLong
Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?finding
Token-Budget-Aware LLM Reasoningfinding
Token-level Preference Self-Alignment Optimization for Multi-style Outline Controllable Generationfinding
TokenShapley: Token Level Context Attribution with Shapley Valuefinding
Tokenisation is NP-CompleteLong
Tokenization is Sensitive to Language Variationfinding
Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Trainingfinding
Tool learning via Inference-time Scaling and Cycle Verifierfinding
ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language ModelsLong
ToolExpNet: Optimizing Multi-Tool Selection in LLMs with Similarity and Dependency-Aware Experience Networksfinding
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool UseLong
ToolSpectrum: Towards Personalized Tool Utilization for Large Language Modelsfinding
Top-n𝜎: Eliminating Noise in Logit Space for Robust Token Sampling of LLMLong
Topic Modeling for Short Texts via Optimal Transport-Based Clusteringfinding
Toward Automatic Discovery of a Canine Phonetic AlphabetLong
Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)finding
Toward Structured Knowledge Reasoning: Contrastive Retrieval-Augmented Generation on Experiencefinding
Towards A Better Initial Policy Model For Scalable Long-CoT Reinforcement Learningfinding
Towards A “Novel” Benchmark: Evaluating Literary Fiction with Large Language Modelsfinding
Towards Adapting Open-Source Large Language Models for Expert-Level Clinical Note Generationfinding
Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generationfinding
Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulnessfinding
Towards Better Evaluation for Generated Patent ClaimsLong
Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environmentsfinding
Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and EnhancementLong
Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian LanguagesLong
Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and MethodLong
Towards Conditioning Clinical Text Generation for User Controlfinding
Towards Context-Robust LLMs: A Gated Representation Fine-tuning ApproachLong
Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human StatesLong
Towards Economical Inference: Enabling DeepSeek’s Multi-Head Latent Attention in Any Transformer-based LLMsLong
Towards Effective Extraction and Evaluation of Factual ClaimsLong
Towards Effective and Efficient Continual Pre-training of Large Language ModelsLong
Towards Efficient LLM Grounding for Embodied Multi-Agent Collaborationfinding
Towards Enhanced Immersion and Agency for LLM-based Interactive DramaLong
Towards Explainable Hate Speech Detectionfinding
Towards Explainable Temporal Reasoning in Large Language Models: A Structure-Aware Generative Frameworkfinding
Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary PerceptionLong
Towards Geo-Culturally Grounded LLM GenerationsShort
Towards Harmonized Uncertainty Estimation for Large Language ModelsLong
Towards LLM-powered Attentive Listener: A Pragmatic Approach through Quantity Self-RepairShort
Towards Medical Complex Reasoning with LLMs through Medical Verifiable Problemsfinding
Towards Multi-dimensional Evaluation of LLM Summarization across Domains and LanguagesLong
Towards Objective Fine-tuning: How LLMs’ Prior Knowledge Causes Potential Poor Calibration?Long
Towards Omni-RAG: Comprehensive Retrieval-Augmented Generation for Large Language Models in Medical ApplicationsLong
Towards Reliable Large Audio Language Modelfinding
Towards Reward Fairness in RLHF: From a Resource Allocation PerspectiveLong
Towards Robust ESG Analysis Against Greenwashing Risks: Aspect-Action Analysis with Cross-Category GeneralizationLong
Towards Robust Universal Information Extraction: Dataset, Evaluation, and SolutionLong
Towards Robust and Efficient Federated Low-Rank Adaptation with Heterogeneous ClientsLong
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creationfinding
Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddingsfinding
Towards Style Alignment in Cross-Cultural TranslationLong
Towards Text-Image Interleaved RetrievalLong
Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentsfinding
Towards a More Generalized Approach in Open Relation ExtractionLong
Towards the Law of Capacity Gap in Distilling Language ModelsLong
Towards the Pedagogical Steering of Large Language Models for Tutoring: A Case Study with Modeling Productive Failurefinding
Tracing and Dissecting How LLMs Recall Factual Knowledge for Real World QuestionsLong
Tracking Life’s Ups and Downs: Mining Life Events from Social Media Posts for Mental Health AnalysisLong
Tracr-Injection: Distilling Algorithms into Pre-trained Language Modelsfinding
Training Bilingual LMs with Data Constraints in the Targeted Languagefinding
Training Dynamics Underlying Language Model Scaling Laws: Loss Deceleration and Zero-Sum LearningLong
Training Language Model to Critique for Better Refinementfinding
Training Long-Context LLMs Efficiently via Chunk-wise Optimizationfinding
Training Multi-Modal LLMs through Dialogue Planning for HRIfinding
Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutorsfinding
Training-free LLM Merging for Multi-task LearningLong
TransBench: Breaking Barriers for Transferable Graphical User Interface Agents in Dynamic Digital Environmentsfinding
Transferring Textual Preferences to Vision-Language Understanding through Model MergingShort
Translate With Care: Addressing Gender Bias, Neutrality, and Reasoning in Large Language Model Translationsfinding
Translation and Fusion Improves Cross-lingual Information ExtractionLong
Transparentize the Internal and External Knowledge Utilization in LLMs with Trustworthy Citationfinding
Tree-KG: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive DomainsLong
Tree-of-Code: A Self-Growing Tree Framework for End-to-End Code Generation and Execution in Complex Tasksfinding
Tree-of-Debate: Multi-Persona Debate Trees Elicit Critical Thinking for Scientific Comparative AnalysisLong
Tree-of-Evolution: Tree-Structured Instruction Evolution for Code Generation in Large Language ModelsLong
Tree-of-Prompts: Abstracting Control-Flow for Prompt Optimizationfinding
TreeCut: A Synthetic Unanswerable Math Word Problem Dataset for LLM Hallucination EvaluationShort
TreeRAG: Unleashing the Power of Hierarchical Storage for Enhanced Knowledge Retrieval in Long Documentsfinding
TreeRL: LLM Reinforcement Learning with On-Policy Tree SearchLong
TriEmbed: Bridge the Gap between Text and Token Indices with Embedding Reparameterizationfinding
Trick or Neat: Adversarial Ambiguity and Language Model Evaluationfinding
TrimLLM: Progressive Layer Dropping for Domain-Specific LLMsLong
TripCraft: A Benchmark for Spatio-Temporally Fine Grained Travel PlanningLong
TripTailor: A Real-World Benchmark for Personalized Travel Planningfinding
TripleFact: Defending Data Contamination in the Evaluation of LLM-driven Fake News DetectionLong
TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operatorsfinding
Truth Knows No Language: Evaluating Truthfulness Beyond EnglishLong
Tunable LLM-based Proactive Recommendation AgentLong
Turbocharging Web Automation: The Impact of Compressed History Statesfinding
Turning Conversations into Workflows: A Framework to Extract and Evaluate Dialog Workflows for Service AI Agentsfinding
Turning Trash into Treasure: Accelerating Inference of Large Language Models with Token RecyclingLong
Two Intermediate Translations Are Better Than One: Fine-tuning LLMs for Document-level Translation RefinementLong
Typology-Guided Adaptation in Multilingual ModelsLong
UAQFact: Evaluating Factual Knowledge Utilization of LLMs on Unanswerable Questionsfinding
UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language ModelsLong
UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questionsfinding
UCS-SQL: Uniting Content and Structure for Enhanced Semantic Bridging In Text-to-SQLfinding
UI-E2I-Synth: Advancing GUI Grounding with Large-Scale Instruction Synthesisfinding
UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter Efficient Fine-Tuning of Large ModelsLong
UQ-Merge: Uncertainty Guided Multimodal Large Language Model Mergingfinding
USDC: A Dataset of ̲User ̲Stance and ̲Dogmatism in Long ̲Conversationsfinding
UTBoost: Rigorous Evaluation of Coding Agents on SWE-BenchLong
Un-considering Contextual Information: Assessing LLMs’ Understanding of Indexical Elementsfinding
UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs’ MemorizationLong
Unanswerability Evaluation for Retrieval Augmented GenerationLong
Uncertainty Propagation on LLM AgentLong
Uncertainty Unveiled: Can Exposure to More In-context Examples Mitigate Uncertainty for Large Language Models?finding
Uncertainty in Causality: A New FrontierLong
Uncertainty-Aware Contrastive Decodingfinding
Uncertainty-Aware Iterative Preference Optimization for Enhanced LLM ReasoningLong
Uncovering Visual-Semantic Psycholinguistic Properties from the Distributional Structure of Text Embedding SpaceLong
Uncovering the Impact of Chain-of-Thought Reasoning for Direct Preference Optimization: Lessons from Text-to-SQLLong
Understand User Opinions of Large Language Models via LLM-Powered In-the-Moment User Experience Interviewsfinding
Understand the Implication: Learning to Think for Pragmatic Understandingfinding
Understanding Common Ground Misalignment in Goal-Oriented Dialog: A Case-Study with Ubuntu Chat LogsLong
Understanding Cross-Domain Adaptation in Low-Resource Topic ModelingLong
Understanding Impact of Human Feedback via Influence FunctionsLong
Understanding In-Context Machine Translation for Low-Resource Languages: A Case Study on ManchuLong
Understanding Large Language Model Vulnerabilities to Social Bias AttacksLong
Understanding Silent Data Corruption in LLM TrainingLong
Understanding and Meeting Practitioner Needs When Measuring Representational Harms Caused by LLM-Based Systemsfinding
Understanding the Dark Side of LLMs’ Intrinsic Self-CorrectionLong
Understanding the Gap: an Analysis of Research Collaborations in NLP and Language Documentationfinding
Understanding the Influence of Synthetic Data for Text Embeddersfinding
Understanding the Repeat Curse in Large Language Models from a Feature Perspectivefinding
Uni-Retrieval: A Multi-Style Retrieval Framework for STEM’s EducationLong
UniCodec: Unified Audio Codec with Single Domain-Adaptive CodebookLong
UniConv: Unifying Retrieval and Response Generation for Large Language Models in ConversationsLong
UniICL: An Efficient ICL Framework Unifying Compression, Selection, and GenerationLong
UniLR: Unleashing the Power of LLMs on Multiple Legal Tasks with a Unified Legal RetrieverLong
UniRAG: Unified Query Understanding Method for Retrieval Augmented GenerationLong
UniT: One Document, Many Revisions, Too Many Edit Intention Taxonomiesfinding
Unifying Continuous and Discrete Text Diffusion with Non-simultaneous Diffusion ProcessesLong
Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language ModelsLong
Unilogit: Robust Machine Unlearning for LLMs Using Uniform-Target Self-Distillationfinding
Unintended Harms of Value-Aligned LLMs: Psychological and Empirical InsightsLong
Unique Hard Attention: A Tale of Two SidesShort
Unlearning Backdoor Attacks for LLMs with Weak-to-Strong Knowledge Distillationfinding
Unleashing LLM Reasoning Capability via Scalable Question Synthesis from ScratchLong
Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation EngineeringLong
Unlocking LLMs’ Self-Improvement Capacity with Autonomous Learning for Domain Adaptationfinding
Unlocking Recursive Thinking of LLMs: Alignment via Refinementfinding
Unlocking Speech Instruction Data Potential with Query Rewritingfinding
Unmasking Style Sensitivity: A Causal Analysis of Bias Evaluation Instability in Large Language ModelsLong
Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model MergingLong
Unraveling and Mitigating Safety Alignment Degradation of Vision-Language Modelsfinding
Unraveling the Mechanics of Learning-Based Demonstration Selection for In-Context LearningLong
Unravelling the Logic: Investigating the Generalisation of Transformers in Numerical Satisfiability ProblemsLong
UnrealLLM: Towards Highly Controllable and Interactable 3D Scene Generation by LLM-powered Procedural Content Generationfinding
Unsolvable Problem Detection: Robust Understanding Evaluation for Large Multimodal ModelsLong
Unsupervised Morphological Tree Tokenizerfinding
Untie the Knots: An Efficient Data Augmentation Strategy for Long-Context Pre-Training in Language ModelsLong
Unveil: Unified Visual-Textual Integration and Distillation for Multi-modal Document RetrievalLong
Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive ParaphrasingLong
Unveiling Confirmation Bias in Chain-of-Thought Reasoningfinding
Unveiling Cultural Blind Spots: Analyzing the Limitations of mLLMs in Procedural Text ComprehensionLong
Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit ViewLong
Unveiling Language-Specific Features in Large Language Models via Sparse AutoencodersLong
Unveiling Privacy Risks in LLM Agent MemoryLong
Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challengesfinding
Unveiling and Addressing Pseudo Forgetting in Large Language Modelsfinding
Unveiling the Key Factors for Distilling Chain-of-Thought Reasoningfinding
Unveiling the Lack of LVLM Robustness to Fundamental Visual Variations: Why and Path Forwardfinding
Unveiling the Potential of BERT-family: A New Recipe for Building Scalable, General and Competitive Large Language ModelsLong
Unveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine TranslationLong
Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter MergingLong
UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban SpacesLong
User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMsfinding
User-side Model Consistency Monitoring for Open Source Large Language Models Inference ServicesLong
Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-AccentLong
Using Shapley interactions to understand how models use structureLong
Using Subtext to Enhance Generative IDRRShort
Utilizing Semantic Textual Similarity for Clinical Survey Data Feature Selectionfinding
V-ALPHASOCIAL: Benchmark and Self-Reflective Chain-of-Thought Generation for Visual Social Commonsense Reasoningfinding
V-Oracle: Making Progressive Reasoning in Deciphering Oracle Bones for You and MeLong
VADE: Visual Attention Guided Hallucination Detection and Eliminationfinding
VAQUUM: Are Vague Quantifiers Grounded in Visual Data?finding
VCD: A Dataset for Visual Commonsense Discovery in Imagesfinding
VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC VideosLong
VISA: Retrieval Augmented Generation with Visual Source AttributionLong
VISIAR: Empower MLLM for Visual Story Ideationfinding
VITAL: A New Dataset for Benchmarking Pluralistic Alignment in HealthcareLong
VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual CuesLong
VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a ServiceLong
VLSBench: Unveiling Visual Leakage in Multimodal SafetyLong
VMLU Benchmarks: A comprehensive benchmark toolkit for Vietnamese LLMsLong
VP-MEL: Visual Prompts Guided Multimodal Entity Linkingfinding
VQAGuider: Guiding Multimodal Large Language Models to Answer Complex Video QuestionsLong
VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward MechanismLong
VSCBench: Bridging the Gap in Vision-Language Model Safety Calibrationfinding
Value Portrait: Assessing Language Models’ Values through Psychometrically and Ecologically Valid ItemsLong
Value Residual LearningLong
Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media ContextsLong
Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMsfinding
Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-trainingLong
Veracity Bias and Beyond: Uncovering LLMs’ Hidden Beliefs in Problem-Solving ReasoningLong
Verbosity-Aware Rationale Reduction: Sentence-Level Rationale Reduction for Efficient and Effective Reasoningfinding
Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metricsfinding
Verifying the Steps of Deductive Reasoning Chainsfinding
ViGiL3D: A Linguistically Diverse Dataset for 3D Visual GroundingLong
VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generationfinding
VideoRAG: Retrieval-Augmented Generation over Video Corpusfinding
VideoVista-CulturalLingo: 360° Horizons-Bridging Cultures, Languages, and Domains in Video ComprehensionLong
Visibility as Survival: Generalizing NLP for Native Alaskan Language Identificationfinding
Vision Language Model Helps Private Information De-Identification in Vision Datafinding
Vision-Language Models Struggle to Align Entities across Modalitiesfinding
Vision-aided Unsupervised Constituency Parsing with Multi-MLLM Debatingfinding
Visual Cues Enhance Predictive Turn-Taking for Two-Party Human Interactionfinding
Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language ModelsLong
Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Modelsfinding
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree SearchLong
Voting or Consensus? Decision-Making in Multi-Agent Debatefinding
VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language ModelsLong
Vulnerability of LLMs to Vertically Aligned Text ManipulationsLong
Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approachfinding
WAFFLE: Fine-tuning Multi-Modal Model for Automated Front-End DevelopmentLong
WASA: WAtermark-based Source Attribution for Large Language Model-Generated Datafinding
WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation WatermarksLong
WMT24++: Expanding the Language Coverage of WMT24 to 55 Languages & Dialectsfinding
WXImpactBench: A Disruptive Weather Impact Understanding Benchmark for Evaluating Large Language Modelsfinding
Wait, that’s not an option: LLMs Robustness with Incorrect Multiple-Choice OptionsLong
Walk in Others’ Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective TransformationLong
Wanda++: Pruning Large Language Models via Regional Gradientsfinding
War of Thoughts: Competition Stimulates Stronger Reasoning in Large Language Modelsfinding
Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State GenerationLong
WarriorCoder: Learning from Expert Battles to Augment Code Large Language ModelsLong
Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality EstimationLong
Watermarking Large Language Models: An Unbiased and Low-risk MethodLong
WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue ModelsLong
We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?Long
Weak-to-Strong Honesty Alignment via Learning-to-Rank Supervisionfinding
Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual ChainsLong
WebNLG-IT: Construction of an aligned RDF-Italian corpus through Machine Translation techniquesfinding
WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Codefinding
WebWalker: Benchmarking LLMs in Web TraversalLong
Weed Out, Then Harvest: Dual Low-Rank Adaptation is an Effective Noisy Label Detector for Noise-Robust Learningfinding
Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decodingfinding
What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient PerspectiveLong
What Is That Talk About? A Video-to-Text Summarization Dataset for Scientific PresentationsLong
What Language Do Non-English-Centric Large Language Models Think in?finding
What Makes a Good Natural Language Prompt?Long
What Matters in Evaluating Book-Length Stories? A Systematic Study of Long Story EvaluationLong
What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMsLong
What are the Essential Factors in Crafting Effective Long Context Multi-Hop Instruction Datasets? Insights and Best PracticesLong
What is Stigma Attributed to? A Theory-Grounded, Expert-Annotated Interview Corpus for Demystifying Mental-Health StigmaLong
What is in a name? Mitigating Name Bias in Text Embedding Similarity via Anonymizationfinding

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.