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
MathD2: Towards Disambiguation of Mathematical Terms
MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion
Math Neurosurgery: Isolating Language Models' Math Reasoning Abilities Using Only Forward Passes
\mathsfCon Instruction: Universal Jailbreaking of Multimodal Large Language Models via Non-Textual Modalities
\mathttGeLLM³O: Generalizing Large Language Models for Multi-property Molecule Optimization
Matina: A Culturally-Aligned Persian Language Model Using Multiple LoRA Experts
MaXIFE: Multilingual and Cross-lingual Instruction Following Evaluation
Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval
Maximizing the Effectiveness of Larger BERT Models for Compression
Maximum Score Routing For Mixture-of-Experts
McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models
McGill-NLP at SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection
MC-MKE: A Fine-Grained Multimodal Knowledge Editing Benchmark Emphasizing Modality Consistency
MCQFormatBench: Robustness Tests for Multiple-Choice Questions
MCS-Bench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in Chinese Classical Studies
MDBench: A Synthetic Multi-Document Reasoning Benchmark Generated with Knowledge Guidance
MDCure: A Scalable Pipeline for Multi-Document Instruction-Following
MDIT-Bench: Evaluating the Dual-Implicit Toxicity in Large Multimodal Models
Meaning Beyond Truth Conditions: Evaluating Discourse Level Understanding via Anaphora Accessibility
Meaning Variation and Data Quality in the Corpus of Founding Era American English
Measure only what is measurable: towards conversation requirements for evaluating task-oriented dialogue systems
Measuring Bias and Agreement in Large Language Model Presupposition Judgments
Measuring Data Diversity for Instruction Tuning: A Systematic Analysis and A Reliable Metric
Measuring Gender Bias in Language Models in Farsi
Measuring Label Ambiguity in Subjective Tasks using Predictive Uncertainty Estimation
Measuring Social Biases in Masked Language Models by Proxy of Prediction Quality
Measuring temporal effects of agent knowledge by date-controlled tool use
Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks
Measuring What Makes You Unique: Difference-Aware User Modeling for Enhancing LLM Personalization
Measuring What Matters: Evaluating Ensemble LLMs with Label Refinement in Inductive Coding
Mechanistic Interpretability of Emotion Inference in Large Language Models
MECoT: Markov Emotional Chain-of-Thought for Personality-Consistent Role-Playing
MedCite: Can Language Models Generate Verifiable Text for Medicine?
MEDDxAgent: A Unified Modular Agent Framework for Explainable Automatic Differential Diagnosis
MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notes
Medical Graph RAG: Evidence-based Medical Large Language Model via Graph Retrieval-Augmented Generation
MedPlan: A Two-Stage RAG-Based System for Personalized Medical Plan Generation
MedSummRAG: Domain-Specific Retrieval for Medical Summarization
MegaAgent: A Large-Scale Autonomous LLM-based Multi-Agent System Without Predefined SOPs
MegaPairs: Massive Data Synthesis for Universal Multimodal Retrieval
MEGen: Generative Backdoor into Large Language Models via Model Editing
MEIT: Multimodal Electrocardiogram Instruction Tuning on Large Language Models for Report Generation
MELABenchv1: Benchmarking Large Language Models against Smaller Fine-Tuned Models for Low-Resource Maltese NLP
MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agents
MemeDetoxNet: Balancing Toxicity Reduction and Context Preservation
MemeQA: Holistic Evaluation for Meme Understanding
MEMERAG: A Multilingual End-to-End Meta-Evaluation Benchmark for Retrieval Augmented Generation
MEMIT-Merge: Addressing MEMIT's Key-Value Conflicts in Same-Subject Batch Editing for LLMs
Memorization: A Close Look at Books
Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation

« prev Page 49/87 next »