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
Enhancing Tool Learning in Large Language Models with Hierarchical Error Checklists
Enhancing Transformation from Natural Language to Signal Temporal Logic Using LLMs with Diverse External Knowledge
Enhancing Transformers for Generalizable First-Order Logical Entailment
Enhancing Unsupervised Sentence Embeddings via Knowledge-Driven Data Augmentation and Gaussian-Decayed Contrastive Learning
EnigmaToM: Improve LLMs' Theory-of-Mind Reasoning Capabilities with Neural Knowledge Base of Entity States
Enough Coin Flips Can Make LLMs Act Bayesian
Enriching children’s stories with LLMs: Delivering multilingual data enrichment for children’s books at scale and across markets
Ensemble Watermarks for Large Language Models
EnSToM: Enhancing Dialogue Systems with Entropy-Scaled Steering Vectors for Topic Maintenance
Entailed Between the Lines: Incorporating Implication into NLI
Entailment-Preserving First-order Logic Representations in Natural Language Entailment
Entity Framing and Role Portrayal in the News
Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems
Entropy-based Exploration Conduction for Multi-step Reasoning
Entrospect: Information-Theoretic Self-Reflection Elicits Better Response Refinement of Small Language Models
EpiCoDe: Boosting Model Performance Beyond Training with Extrapolation and Contrastive Decoding
EpMAN: Episodic Memory AttentioN for Generalizing to Longer Contexts
EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning
Error Comparison Optimization for Large Language Models on Aspect-Based Sentiment Analysis
Error-driven Data-efficient Large Multimodal Model Tuning
ERU-KG: Efficient Reference-aligned Unsupervised Keyphrase Generation
EscapeBench: Towards Advancing Creative Intelligence of Language Model Agents
ESF: Efficient Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models
EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models
Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis
Estimating Privacy Leakage of Augmented Contextual Knowledge in Language Models
Estimation of Text Difficulty in the Context of Language Learning
Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation
ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries
EtiCor++: Towards Understanding Etiquettical Bias in LLMs
ETRQA: A Comprehensive Benchmark for Evaluating Event Temporal Reasoning Abilities of Large Language Models
EuroVerdict: A Multilingual Dataset for Verdict Generation Against Misinformation
Evading Toxicity Detection with ASCII-art: A Benchmark of Spatial Attacks on Moderation Systems
Evaluating Credibility and Political Bias in LLMs for News Outlets in Bangladesh
Evaluating Design Decisions for Dual Encoder-based Entity Disambiguation
Evaluating Implicit Bias in Large Language Models by Attacking From a Psychometric Perspective
Evaluating Instructively Generated Statement by Large Language Models for Directional Event Causality Identification
Evaluating Intermediate Reasoning of Code-Assisted Large Language Models for Mathematics
Evaluating Language Models as Synthetic Data Generators
Evaluating Large Language Models for Confidence-based Check Set Selection
Evaluating Lexical Proficiency in Neural Language Models
Evaluating LLMs' Assessment of Mixed-Context Hallucination Through the Lens of Summarization
Evaluating LLMs for Portuguese Sentence Simplification with Linguistic Insights
Evaluating LLMs' Mathematical and Coding Competency through Ontology-guided Interventions
Evaluating LLMs with Multiple Problems at once
Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users
Evaluating Multimodal Large Language Models on Video Captioning via Monte Carlo Tree Search
Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
Evaluating Pretrained Causal Language Models for Synonymy
Evaluating Retrieval Augmented Generation to Communicate UK Climate Change Information

« prev Page 27/87 next »