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
S³ - Semantic Signal Separation
Saama Technologies at SemEval-2025 Task 8: Few-shot prompting with LLM-generated examples for question answering on tabular data
SabiYarn: Advancing Low Resource Languages with Multitask NLP Pretraining
SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities
Safe: Enhancing Mathematical Reasoning in Large Language Models via Retrospective Step-aware Formal Verification
SafeEraser: Enhancing Safety in Multimodal Large Language Models through Multimodal Machine Unlearning
Safeguarding RAG Pipelines with GMTP: A Gradient-based Masked Token Probability Method for Poisoned Document Detection
Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs
SafeLawBench: Towards Safe Alignment of Large Language Models
SafeRAG: Benchmarking Security in Retrieval-Augmented Generation of Large Language Model
Safer or Luckier? LLMs as Safety Evaluators Are Not Robust to Artifacts
SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
Safety Alignment via Constrained Knowledge Unlearning
Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety
SAKE: Steering Activations for Knowledge Editing
Sakura at SemEval-2025 Task 2: Enhancing Named Entity Translation with Fine-Tuning and Preference Optimization
SALT at SemEval-2025 Task 2: A SQL-based Approach for LLM-Free Entity-Aware-Translation
SAM Decoding: Speculative Decoding via Suffix Automaton
Same Company, Same Signal: The Role of Identity in Earnings Call Transcripts
Sample-Efficient Human Evaluation of Large Language Models via Maximum Discrepancy Competition
Sampling-based Pseudo-Likelihood for Membership Inference Attacks
Samsung Research Poland at SemEval-2025 Task 8: LLM ensemble methods for QA over tabular data
SANCTUARY: An Efficient Evidence-based Automated Fact Checking System
Sandcastles in the Storm: Revisiting the (Im)possibility of Strong Watermarking
SANSKRITI: A Comprehensive Benchmark for Evaluating Language Models' Knowledge of Indian Culture
SARA: Salience-Aware Reinforced Adaptive Decoding for Large Language Models in Abstractive Summarization
SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage
SBU-NLP at SemEval-2025 Task 8: Self-Correction and Collaboration in LLMs for Tabular Question Answering
Scalable Vision Language Model Training via High Quality Data Curation
ScaleBiO: Scalable Bilevel Optimization for LLM Data Reweighting
SCALE: Towards Collaborative Content Analysis in Social Science with Large Language Model Agents and Human Intervention
Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing
Scaling LLMs' Social Reasoning: Sprinkle Cognitive "Aha Moment" into Fundamental Long-thought Logical Capabilities
Scaling Species Diversity Analysis in Carbon Credit Projects with Large-Context LLMs
Scaling Text-Rich Image Understanding via Code-Guided Synthetic Multimodal Data Generation
Scaling Under-Resourced TTS: A Data-Optimized Framework with Advanced Acoustic Modeling for Thai
Scaling up the State Size of RNN LLMs for Long-Context Scenarios
ScanEZ: Integrating Cognitive Models with Self-Supervised Learning for Spatiotemporal Scanpath Prediction
SCAR: Data Selection via Style Consistency-Aware Response Ranking for Efficient Instruction-Tuning of Large Language Models
ScEdit: Script-based Assessment of Knowledge Editing
SceneGenAgent: Precise Industrial Scene Generation with Coding Agent
SceneGram: Conceptualizing and Describing Tangrams in Scene Context
SciBERT Meets Contrastive Learning: A Solution for Scientific Hallucination Detection
Sci-LoRA: Mixture of Scientific LoRAs for Cross-Domain Lay Paraphrasing
SCITAT: A Question Answering Benchmark for Scientific Tables and Text Covering Diverse Reasoning Types
SciVer: Evaluating Foundation Models for Multimodal Scientific Claim Verification
SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems
SciVQA 2025: Overview of the First Scientific Visual Question Answering Shared Task
SConU: Selective Conformal Uncertainty in Large Language Models
SCOPE: Compress Mathematical Reasoning Steps for Efficient Automated Process Annotation

« prev Page 67/87 next »