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
Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs
Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training
TokenShapley: Token Level Context Attribution with Shapley Value
Tone in Perspective: A Computational Typological Analysis of Tone Function in ASR
ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language Models
ToolExpNet: Optimizing Multi-Tool Selection in LLMs with Similarity and Dependency-Aware Experience Networks
ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use
Tool learning via Inference-time Scaling and Cycle Verifier
ToolReAGt: Tool Retrieval for LLM-based Complex Task Solution via Retrieval Augmented Generation
ToolSpectrum: Towards Personalized Tool Utilization for Large Language Models
Too Polite to be Human: Evaluating LLM Empathy in Korean Conversations via a DCT-Based Framework
Topic Modeling for Short Texts via Optimal Transport-Based Clustering
Top-nσ: Eliminating Noise in Logit Space for Robust Token Sampling of LLM
Tore-Klose: Record Scorer, Goal Hunter, Machine? Human Association Norms for German Personal Name Compounds
Toward Automatic Discovery of a Canine Phonetic Alphabet
Toward Global AI Inclusivity: A Large-Scale Multilingual Terminology Dataset (GIST)
Toward Reasonable Parrots: Why Large Language Models Should Argue with Us by Design
Towards A Better Initial Policy Model For Scalable Long-CoT Reinforcement Learning
Towards Adapting Open-Source Large Language Models for Expert-Level Clinical Note Generation
Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation
Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agents
Towards a More Generalized Approach in Open Relation Extraction
Towards A "Novel" Benchmark: Evaluating Literary Fiction with Large Language Models
Towards a Principled Evaluation of Knowledge Editors
Towards a Real-time Swedish Speech Analyzer for Language Learning Games: A Hybrid AI Approach to Language Assessment
Towards Automatic Formal Feedback on Scientific Documents
Towards Better Chain-of-Thought: A Reflection on Effectiveness and Faithfulness
Towards Better Evaluation for Generated Patent Claims
Towards Better Open-Ended Text Generation: A Multicriteria Evaluation Framework
Towards Better Understanding of Program-of-Thought Reasoning in Cross-Lingual and Multilingual Environments
Towards Better Value Principles for Large Language Model Alignment: A Systematic Evaluation and Enhancement
Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages
Towards compact and efficient Slovak summarization models
Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and Method
Towards Comprehensive Evaluation of Open-Source Language Models: A Multi-Dimensional, User-Driven Approach
Towards Conditioning Clinical Text Generation for User Control
Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach
Towards Dynamic Theory of Mind: Evaluating LLM Adaptation to Temporal Evolution of Human States
Towards Economical Inference: Enabling DeepSeek's Multi-Head Latent Attention in Any Transformer-based LLMs
Towards Effective and Efficient Continual Pre-training of Large Language Models
Towards Effective Extraction and Evaluation of Factual Claims
Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration
Towards Enhanced Immersion and Agency for LLM-based Interactive Drama
Towards Explainable Hate Speech Detection
Towards Explainable Temporal Reasoning in Large Language Models: A Structure-Aware Generative Framework
Towards Fairness Assessment of Dutch Hate Speech Detection
Towards Fully Exploiting LLM Internal States to Enhance Knowledge Boundary Perception
Towards Generating Controllable and Solvable Geometry Problem by Leveraging Symbolic Deduction Engine
Towards Geo-Culturally Grounded LLM Generations

« prev Page 78/87 next »