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
Planning with Diffusion Models for Target-Oriented Dialogue Systems
PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play
PL-Guard: Benchmarking Language Model Safety for Polish
Plug-in and Fine-tuning: Bridging the Gap between Small Language Models and Large Language Models
PM3-KIE: A Probabilistic Multi-Task Meta-Model for Document Key Information Extraction
PodAgent: A Comprehensive Framework for Podcast Generation
Polarity inversion operators in PLM
Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean
PoliTo at SemEval-2025 Task 1: Beyond Literal Meaning: A Chain-of-Though Approach for Multimodal Idiomacity Understanding
PolyNarrative: A Multilingual, Multilabel, Multi-domain Dataset for Narrative Extraction from News Articles
Ponder & Press: Advancing Visual GUI Agent towards General Computer Control
PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment
Portuguese Automated Fact-checking: Information Retrieval with Claim extraction
Position-aware Automatic Circuit Discovery
Position-Aware Depth Decay Decoding (D³): Boosting Large Language Model Inference Efficiency
Position Paper: MeMo: Towards Language Models with Associative Memory Mechanisms
Positive Experience Reflection for Agents in Interactive Text Environments
Powerformer: Efficient and High-Accuracy Privacy-Preserving Language Model with Homomorphic Encryption
Power(ful) Associations: Rethinking “Stereotype” for NLP
PPT: A Minor Language News Recommendation Model via Cross-Lingual Preference Pattern Transfer
PQR: Improving Dense Retrieval via Potential Query Modeling
Practical Solutions to Practical Problems in Developing Argument Mining Systems
Praetor: A Fine-Grained Generative LLM Evaluator with Instance-Level Customizable Evaluation Criteria
Pragmatic Perspective on Assessing Implicit Meaning Interpretation in Sentiment Analysis Models
Pragmatics in the Era of Large Language Models: A Survey on Datasets, Evaluation, Opportunities and Challenges
PRAISE: Enhancing Product Descriptions with LLM-Driven Structured Insights
Pre³: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation
P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts
Pre-annotation Matters: A Comparative Study on POS and Dependency Annotation for an Alsatian Dialect
PreClinIE: An Annotated Corpus for Information Extraction in Preclinical Studies
Predicate-Conditional Conformalized Answer Sets for Knowledge Graph Embeddings
PredictaBoard: Benchmarking LLM Score Predictability
Predicting Depression in Screening Interviews from Interactive Multi-Theme Collaboration
Predicting Emotion Intensity in Text Using Transformer-Based Models
Predicting Implicit Arguments in Procedural Video Instructions
Predicting The Scholarly Impact of Research Papers Using Retrieval-Augmented LLMs
Predicting Through Generation: Why Generation Is Better for Prediction
Predicting Turn-Taking and Backchannel in Human-Machine Conversations Using Linguistic, Acoustic, and Visual Signals
Prediction-Augmented Generation for Automatic Diagnosis Tasks
Prediction Hubs are Context-Informed Frequent Tokens in LLMs
Preference Curriculum: LLMs Should Always Be Pretrained on Their Preferred Data
PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy
PreSumm: Predicting Summarization Performance Without Summarizing
Pretraining Context Compressor for Large Language Models with Embedding-Based Memory
Pre-Training Curriculum for Multi-Token Prediction in Language Models
Pre-training Distillation for Large Language Models: A Design Space Exploration
Pretraining Strategies using Monolingual and Parallel Data for Low-Resource Machine Translation
Preventing Rogue Agents Improves Multi-Agent Collaboration
Principal Parts Detection for Computational Morphology: Task, Models and Benchmark
Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries

« prev Page 59/87 next »