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
Rethinking Diverse Human Preference Learning through Principal Component Analysis
Rethinking Evaluation Metrics for Grammatical Error Correction: Why Use a Different Evaluation Process than Human?
Rethinking Full Finetuning from Pretraining Checkpoints in Active Learning for African Languages
Rethinking KenLM: Good and Bad Model Ensembles for Efficient Text Quality Filtering in Large Web Corpora
Rethinking Prompt-based Debiasing in Large Language Model
Rethinking Repetition Problems of LLMs in Code Generation
Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization
Rethinking Semantic Parsing for Large Language Models: Enhancing LLM Performance with Semantic Hints
Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges
Rethinking Table Instruction Tuning
Rethinking the Role of Prompting Strategies in LLM Test-Time Scaling: A Perspective of Probability Theory
Retrieval-Augmented Fine-Tuning With Preference Optimization For Visual Program Generation
Retrieval-Augmented Forecasting with Tabular Time Series Data
Retrieval-Augmented Generation Meets Local Languages for Improved Drug Information Access and Comprehension.
Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning
Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models
Retrieve to Explain: Evidence-driven Predictions for Explainable Drug Target Identification
Retrieving Argument Graphs Using Vision Transformers
Retrofitting Large Language Models with Dynamic Tokenization
RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation
Retrospective Learning from Interactions
RETUYT-INCO at BEA 2025 Shared Task: How Far Can Lightweight Models Go in AI-powered Tutor Evaluation?
Revealing and Mitigating the Local Pattern Shortcuts of Mamba
Revealing Hidden Mechanisms of Cross-Country Content Moderation with Natural Language Processing
Revealing the Deceptiveness of Knowledge Editing: A Mechanistic Analysis of Superficial Editing
Reversal of Thought: Enhancing Large Language Models with Preference-Guided Reverse Reasoning Warm-up
Reverse Preference Optimization for Complex Instruction Following
Review-Instruct: A Review-Driven Multi-Turn Conversations Generation Method for Large Language Models
Revisiting 3D LLM Benchmarks: Are We Really Testing 3D Capabilities?
Revisiting Classical Chinese Event Extraction with Ancient Literature Information
Revisiting Common Assumptions about Arabic Dialects in NLP
Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability
Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models' Uncertainty?
Revisiting In-Context Learning with Long Context Language Models
Revisiting Knowledge Distillation for Autoregressive Language Models
Revisiting LLMs as Zero-Shot Time Series Forecasters: Small Noise Can Break Large Models
Revisiting LoRA through the Lens of Parameter Redundancy: Spectral Encoding Helps
Revisiting Scaling Laws for Language Models: The Role of Data Quality and Training Strategies
Revisiting Self-Consistency from Dynamic Distributional Alignment Perspective on Answer Aggregation
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
Revisiting Token Dropping Strategy in Efficient BERT Pretraining
Revisiting Uncertainty Quantification Evaluation in Language Models: Spurious Interactions with Response Length Bias Results
Revisiting Weak-to-Strong Generalization in Theory and Practice: Reverse KL vs. Forward KL
Revisit Self-Debugging with Self-Generated Tests for Code Generation
Reviving Cultural Heritage: A Novel Approach for Comprehensive Historical Document Restoration
REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space
REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective
Reward Generalization in RLHF: A Topological Perspective
Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness Instruction

« prev Page 65/87 next »