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
UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces
USDC: A Dataset of \underlineUser \underlineStance and \underlineDogmatism in Long \underlineConversations
User Behavior Prediction as a Generic, Robust, Scalable, and Low-Cost Evaluation Strategy for Estimating Generalization in LLMs
User Feedback Alignment for LLM-powered Interest Exploration in Large-scale Recommendation Systems
User-side Model Consistency Monitoring for Open Source Large Language Models Inference Services
Using Humor to Bypass Safety Guardrails in Large Language Models
Using Information Theory to Characterize Prosodic Typology: The Case of Tone, Pitch-Accent and Stress-Accent
Using Large Language Models to Perform MIPVU-Inspired Automatic Metaphor Detection
Using LLM Judgements for Sanity Checking Results and Reproducibility of Human Evaluations in NLP
Using LLMs and Preference Optimization for Agreement-Aware HateWiC Classification
Using NLI to Identify Potential Collocation Transfer in L2 English
Using Shapley interactions to understand how models use structure
Using Subtext to Enhance Generative IDRR
Ustnlp16 at SemEval-2025 Task 9: Improving Model Performance through Imbalance Handling and Focal Loss
UTBNLP at Semeval-2025 Task 11: Predicting Emotion Intensity with BERT and VAD-Informed Attention.
UTBoost: Rigorous Evaluation of Coding Agents on SWE-Bench
UTF: Under-trained Tokens as Fingerprints —— a Novel Approach to LLM Identification
Utilizing Semantic Textual Similarity for Clinical Survey Data Feature Selection
UT-NLP at SemEval-2025 Task 11: Evaluating Zero-Shot Capability of GPT-4o mini on Emotion Recognition via Role-Play and Contrastive Judging
UTSamuel at ArchEHR-QA 2025: A Clinical Question Answering System for Responding to Patient Portal Messages Using Generative AI
UWBa at SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
UZH at SemEval-2025 Task 3: Token-Level Self-Consistency for Hallucination Detection
VADE: Visual Attention Guided Hallucination Detection and Elimination
V-ALPHASOCIAL: Benchmark and Self-Reflective Chain-of-Thought Generation for Visual Social Commonsense Reasoning
Value Portrait: Assessing Language Models' Values through Psychometrically and Ecologically Valid Items
Value Residual Learning
Value-Spectrum: Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts
VAQUUM: Are Vague Quantifiers Grounded in Visual Data?
Variable Layerwise Quantization: A Simple and Effective Approach to Quantize LLMs
Variety delights (sometimes) - Annotation differences in morphologically annotated corpora
VaseVQA: Multimodal Agent and Benchmark for Ancient Greek Pottery
VCD: A Dataset for Visual Commonsense Discovery in Images
Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training
Veracity Bias and Beyond: Uncovering LLMs' Hidden Beliefs in Problem-Solving Reasoning
VerbaNexAI at SemEval-2025 Task 11 Track A: A RoBERTa-Based Approach for the Classification of Emotions in Text
VerbaNexAI at SemEval-2025 Task 2: Enhancing Entity-Aware Translation with Wikidata-Enriched MarianMT
VerbaNexAI at SemEval-2025 Task 3: Fact Retrieval with Google Snippets for LLM Context Filtering to identify Hallucinations
VerbaNexAI at SemEval-2025 Task 9: Advances and Challenges in the Automatic Detection of Food Hazards
Verbosity-Aware Rationale Reduction: Sentence-Level Rationale Reduction for Efficient and Effective Reasoning
VeReaFine: Iterative Verification Reasoning Refinement RAG for Hallucination-Resistant on Open-Ended Clinical QA
Verifying the Steps of Deductive Reasoning Chains
Verify with Caution: The Pitfalls of Relying on Imperfect Factuality Metrics
VF-Eval: Evaluating Multimodal LLMs for Generating Feedback on AIGC Videos
VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation
VideoRAG: Retrieval-Augmented Generation over Video Corpus
VideoVista-CulturalLingo: 360° Horizons-Bridging Cultures, Languages, and Domains in Video Comprehension
ViGiL3D: A Linguistically Diverse Dataset for 3D Visual Grounding
VISA: Retrieval Augmented Generation with Visual Source Attribution
VISIAR: Empower MLLM for Visual Story Ideation
Visibility as Survival: Generalizing NLP for Native Alaskan Language Identification

« prev Page 83/87 next »