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
Vision-aided Unsupervised Constituency Parsing with Multi-MLLM Debating
Vision Language Model Helps Private Information De-Identification in Vision Data
Vision-Language Models Struggle to Align Entities across Modalities
VisTRA: Visual Tool-use Reasoning Analyzer for Small Object Visual Question Answering
Visual Cues Enhance Predictive Turn-Taking for Two-Party Human Interaction
Visual Evidence Prompting Mitigates Hallucinations in Large Vision-Language Models
Visualising Policy-Reward Interplay to Inform Zeroth-Order Preference Optimisation of Large Language Models
Visual Question Answering on Scientific Charts Using Fine-Tuned Vision-Language Models
Visual Representations of Temporal Relations between Events and Time Expressions in News Stories
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
VITAL: A New Dataset for Benchmarking Pluralistic Alignment in Healthcare
VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues
VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service
VLSBench: Unveiling Visual Leakage in Multimodal Safety
VMLU Benchmarks: A comprehensive benchmark toolkit for Vietnamese LLMs
Voices of Dissent: A Multimodal Analysis of Protest Songs through Lyrics and Audio
V-Oracle: Making Progressive Reasoning in Deciphering Oracle Bones for You and Me
Vorm: Translations and a constrained hypothesis space support unsupervised morphological segmentation across languages
Voting or Consensus? Decision-Making in Multi-Agent Debate
VoxEval: Benchmarking the Knowledge Understanding Capabilities of End-to-End Spoken Language Models
VoxRAG: A Step Toward Transcription-Free RAG Systems in Spoken Question Answering
VP-MEL: Visual Prompts Guided Multimodal Entity Linking
VQAGuider: Guiding Multimodal Large Language Models to Answer Complex Video Questions
VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism
VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration
Vulnerability of LLMs to Vertically Aligned Text Manipulations
Vulnerability of Text-to-Image Models to Prompt Template Stealing: A Differential Evolution Approach
Vuyko Mistral: Adapting LLMs for Low-Resource Dialectal Translation
WAFFLE: Fine-tuning Multi-Modal Model for Automated Front-End Development
Walk in Others' Shoes with a Single Glance: Human-Centric Visual Grounding with Top-View Perspective Transformation
wangkongqiang at SemEval-2025 Task 11:Bridging the Gap in Text-Based Emotion Detection
Wanted: Personalised Bias Warnings for Gender Bias in Language Models
Warmup Generations: A Task-Agnostic Approach for Guiding Sequence-to-Sequence Learning with Unsupervised Initial State Generation
War of Thoughts: Competition Stimulates Stronger Reasoning in Large Language Models
WarriorCoder: Learning from Expert Battles to Augment Code Large Language Models
WASA: WAtermark-based Source Attribution for Large Language Model-Generated Data
Watching the Watchers: Exposing Gender Disparities in Machine Translation Quality Estimation
Watermarking Large Language Models: An Unbiased and Low-risk Method
WavRAG: Audio-Integrated Retrieval Augmented Generation for Spoken Dialogue Models
WC Team at SemEval-2025 Task 6: PromiseEval: Multinational, Multilingual, Multi-Industry Promise Verification leveraging monolingual and multilingual BERT models
Weakest Link in the Chain: Security Vulnerabilities in Advanced Reasoning Models
Weak-to-Strong Honesty Alignment via Learning-to-Rank Supervision
Weaving Context Across Images: Improving Vision-Language Models through Focus-Centric Visual Chains
Web(er) of Hate: A Survey on How Hate Speech Is Typed
Webis at CQs-Gen 2025: Prompting and Reranking for Critical Questions
WebNLG-IT: Construction of an aligned RDF-Italian corpus through Machine Translation techniques
WebUIBench: A Comprehensive Benchmark for Evaluating Multimodal Large Language Models in WebUI-to-Code
Weed Out, Then Harvest: Dual Low-Rank Adaptation is an Effective Noisy Label Detector for Noise-Robust Learning
Weight-of-Thought Reasoning: Exploring Neural Network Weights for Enhanced LLM Reasoning
Well Begun is Half Done: Low-resource Preference Alignment by Weak-to-Strong Decoding

« prev Page 84/87 next »