ACL 2025

4,324 papers

Top Research Directions

Research directions most represented by ACL 2025 papers.

Factual Inaccuracy and Hallucination in Large Language Models 130
Shifting from Static Benchmarks to Dynamic Evaluation 120
Grounding Language Models with External Knowledge Retrieval 110
Evaluating Generative AI with Large Language Models 84
Intermediate Reasoning Chains for Deliberative Inference 80
Contextual Distraction and Noise Sensitivity in Language Models 78
Task Activation via In Context Demonstrations 66
Mitigating Data Scarcity in Low Resource Language Processing 65
Iterative Retrieval Augmented Generation for Multi Hop Reasoning 60
Autonomous Code Refinement via Execution Feedback Loops 60
The Language Bias of English Centric Benchmarks 54
Scaling Training Datasets Using Large Language Models 53
Understanding Prompt Sensitivity in Language Models 48
Role Specialization in Multi-Agent Architectures 47
Modeling Co Occurring and Conflicting Emotional States 47

Top Authors

AuthorPapers
Min Zhang26
Bing Qin19
Maosong Sun19
Minlie Huang17
Zhiyuan Liu16
Le Sun15
Fei Huang14
Preslav Nakov14
Huajun Chen13
Jiaheng Liu13
Xuanjing Huang13
Xuming Hu13
Arman Cohan12
Juntao Li12
Kang Liu12
Taro Watanabe12
Tat-Seng Chua12
Xianpei Han12
Xueqi Cheng12
Yangqiu Song12

Impactful Papers

Papers from ACL 2025 that shaped research clusters.

Foundational

Influential

Papers

Title
Redundancy Principles for MLLMs Benchmarks
Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models
REFIND at SemEval-2025 Task 3: Retrieval-Augmented Factuality Hallucination Detection in Large Language Models
Refining Salience-Aware Sparse Fine-Tuning Strategies for Language Models
Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models
ReflectDiffu: Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework
ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
ReflectionCoder: Learning from Reflection Sequence for Enhanced One-off Code Generation
Reflection on Knowledge Graph for Large Language Models Reasoning
ReflecTool: Towards Reflection-Aware Tool-Augmented Clinical Agents
Ref-Long: Benchmarking the Long-context Referencing Capability of Long-context Language Models
RefreshKV: Updating Small KV Cache During Long-form Generation
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
Registering Source Tokens to Target Language Spaces in Multilingual Neural Machine Translation
Regular-pattern-sensitive CRFs for Distant Label Interactions
Rehearse With User: Personalized Opinion Summarization via Role-Playing based on Large Language Models
Re-identification of De-identified Documents with Autoregressive Infilling
Reinforced IR: A Self-Boosting Framework For Domain-Adapted Information Retrieval
Reinforcement Learning for Adversarial Query Generation to Enhance Relevance in Cold-Start Product Search
Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts
ReKG-MCTS: Reinforcing LLM Reasoning on Knowledge Graphs via Training-Free Monte Carlo Tree Search
RelationalCoder: Rethinking Complex Tables via Programmatic Relational Transformation
ReLearn: Unlearning via Learning for Large Language Models
RelEdit: Evaluating Conceptual Knowledge Editing in Language Models via Relational Reasoning
Relevance Scores Calibration for Ranked List Truncation via TMP Adapter
Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?
Reliably Bounding False Positives: A Zero-Shot Machine-Generated Text Detection Framework via Multiscaled Conformal Prediction
RemoteRAG: A Privacy-Preserving LLM Cloud RAG Service
Removal of Hallucination on Hallucination: Debate-Augmented RAG
Removing Prompt-template Bias in Reinforcement Learning from Human Feedback
RePanda: Pandas-powered Tabular Verification and Reasoning
Representation Bending for Large Language Model Safety
Representations of Fact, Fiction and Forecast in Large Language Models: Epistemics and Attitudes
REPRO-Bench: Can Agentic AI Systems Assess the Reproducibility of Social Science Research?
Reproducing the Argument Quality Prediction of Project Debater
ReproHum #0031-01: Reproducing the Human Evaluation of Readability from “It is AI’s Turn to Ask Humans a Question”
ReproHum #0033-05: Human Evaluation of Factuality from A Multidisciplinary Perspective
ReproHum #0067-01: A Reproduction of the Evaluation of Cross-Lingual Summarization
ReproHum #0669-08: Reproducing Sentiment Transfer Evaluation
ReproHum #0729-04: Human Evaluation Reproduction Report for “MemSum: Extractive Summarization of Long Documents Using Multi-Step Episodic Markov Decision Processes”
ReproHum #0729-04: Partial reproduction of the human evaluation of the MemSum and NeuSum summarisation systems
ReproHum #0744-02: A Reproduction of the Human Evaluation of Meaning Preservation in “Factorising Meaning and Form for Intent-Preserving Paraphrasing”
ReproHum: #0744-02: Investigating the Reproducibility of Semantic Preservation Human Evaluations
Reranking-based Generation for Unbiased Perspective Summarization
Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms
Research Borderlands: Analysing Writing Across Research Cultures
Research Community Perspectives on "Intelligence" and Large Language Models
Resolution-Alignment-Completion of Tabular Electronic Health Records via Meta-Path Generative Sampling
Resource-Friendly Dynamic Enhancement Chain for Multi-Hop Question Answering
Response Wide Shut? Surprising Observations in Basic Vision Language Model Capabilities

« prev Page 64/87 next »