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
Corpus Poisoning via Approximate Greedy Gradient Descent
Correcting Hallucinations in News Summaries: Exploration of Self-Correcting LLM Methods with External Knowledge
Correcting on Graph: Faithful Semantic Parsing over Knowledge Graphs with Large Language Models
CortexDebate: Debating Sparsely and Equally for Multi-Agent Debate
COSMIC: Generalized Refusal Direction Identification in LLM Activations
COSMMIC: Comment-Sensitive Multimodal Multilingual Indian Corpus for Summarization and Headline Generation
Costs and Benefits of AI-Enabled Topic Modeling in P-20 Research: The Case of School Improvement Plans
CoT-based Synthesizer: Enhancing LLM Performance through Answer Synthesis
CoT-ICL Lab: A Synthetic Framework for Studying Chain-of-Thought Learning from In-Context Demonstrations
CoT-UQ: Improving Response-wise Uncertainty Quantification in LLMs with Chain-of-Thought
CoT-Valve: Length-Compressible Chain-of-Thought Tuning
CoT-VTM: Visual-to-Music Generation with Chain-of-Thought Reasoning
Counterfactual-Consistency Prompting for Relative Temporal Understanding in Large Language Models
Counterspeech the ultimate shield! Multi-Conditioned Counterspeech Generation through Attributed Prefix Learning
CourtEval: A Courtroom-Based Multi-Agent Evaluation Framework
CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems
COVER: Context-Driven Over-Refusal Verification in LLMs
CPIQA: Climate Paper Image Question Answering Dataset for Retrieval-Augmented Generation with Context-based Query Expansion
Crab: A Novel Configurable Role-Playing LLM with Assessing Benchmark
CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents
Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings
Cracking Factual Knowledge: A Comprehensive Analysis of Degenerate Knowledge Neurons in Large Language Models
Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence
CrafText Benchmark: Advancing Instruction Following in Complex Multimodal Open-Ended World
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity
Craw4LLM: Efficient Web Crawling for LLM Pretraining
Creating a Lens of Chinese Culture: A Multimodal Dataset for Chinese Pun Rebus Art Understanding
Creating Hierarchical Relations in a Multilingual Event-type Ontology
CrisisTS: Coupling Social Media Textual Data and Meteorological Time Series for Urgency Classification
CRiskEval: A Chinese Multi-Level Risk Evaluation Benchmark Dataset for Large Language Models
CriticalBrew at CQs-Gen 2025: Collaborative Multi-Agent Generation and Evaluation of Critical Questions for Arguments
Critic-CoT: Boosting the Reasoning Abilities of Large Language Model via Chain-of-Thought Critic
CritiQ: Mining Data Quality Criteria from Human Preferences
Croppable Knowledge Graph Embedding
CROSSAGENTIE: Cross-Type and Cross-Task Multi-Agent LLM Collaboration for Zero-Shot Information Extraction
Cross-cultural Sentiment Analysis of Social Media Responses to a Sudden Crisis Event
Cross-Document Event-Keyed Summarization
Cross-Genre Learning for Old English Poetry POS Tagging
Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs
Cross-Lingual Generalization and Compression: From Language-Specific to Shared Neurons
Cross-lingual Multimodal Sentiment Analysis for Low-Resource Languages via Language Family Disentanglement and Rethinking Transfer
Cross-Lingual Optimization for Language Transfer in Large Language Models
Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models
Cross-Lingual Representation Alignment Through Contrastive Image-Caption Tuning
Cross-Lingual Transfer of Cultural Knowledge: An Asymmetric Phenomenon
Cross-Lingual Transfer of Debiasing and Detoxification in Multilingual LLMs: An Extensive Investigation
Cross-modal Clustering-based Retrieval for Scalable and Robust Image Captioning
Cross-model Transferability among Large Language Models on the Platonic Representations of Concepts
Crowd Comparative Reasoning: Unlocking Comprehensive Evaluations for LLM-as-a-Judge
Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia

« prev Page 18/87 next »