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
LLaSE-G1: Incentivizing Generalization Capability for LLaMA-based Speech Enhancement
LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering
LLM Agents for Coordinating Multi-User Information Gathering
LLM Agents Making Agent Tools
LLM as a Broken Telephone: Iterative Generation Distorts Information
LLM-as-an-Interviewer: Beyond Static Testing Through Dynamic LLM Evaluation
LLM as Effective Streaming Processor: Bridging Streaming-Batch Mismatches with Group Position Encoding
LLM as Entity Disambiguator for Biomedical Entity-Linking
LLM-Assisted, Iterative Curriculum Writing: A Human-Centered AI Approach in Finnish Higher Education
LLM-Based Multi-Agent Systems are Scalable Graph Generative Models
LLM-based Rumor Detection via Influence Guided Sample Selection and Game-based Perspective Analysis
LLM-based Translation Inference with Iterative Bilingual Understanding
LLM Braces: Straightening Out LLM Predictions with Relevant Sub-Updates
LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
LLM Dependency Parsing with In-Context Rules
LLM-Driven Estimation of Personal Carbon Footprint from Dialogues
LLM-Empowered Class Imbalanced Graph Prompt Learning for Online Drug Trafficking Detection
LLM-Enhanced Query Generation and Retrieval Preservation for Task-Oriented Dialogue
LLM-Enhanced Self-Evolving Reinforcement Learning for Multi-Step E-Commerce Payment Fraud Risk Detection
LLM-Forest: Ensemble Learning of LLMs with Graph-Augmented Prompts for Data Imputation
LLM-Guided Semantic-Aware Clustering for Topic Modeling
LLM×MapReduce: Simplified Long-Sequence Processing using Large Language Models
LLM Meets Scene Graph: Can Large Language Models Understand and Generate Scene Graphs? A Benchmark and Empirical Study
LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs
LLMs are Biased Evaluators But Not Biased for Fact-Centric Retrieval Augmented Generation
LLMs as Planning Formalizers: A Survey for Leveraging Large Language Models to Construct Automated Planning Models
LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline
LLMs Can Also Do Well! Breaking Barriers in Semantic Role Labeling via Large Language Models
LLMs can be easily Confused by Instructional Distractions
LLMs can Perform Multi-Dimensional Analytic Writing Assessments: A Case Study of L2 Graduate-Level Academic English Writing
LLMs Can Simulate Standardized Patients via Agent Coevolution
LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges
LLMs for Detection and Classification of Persuasion Techniques in Slavic Parliamentary Debates and Social Media Texts
LLMs in alliance with Edit-based models: advancing In-Context Learning for Grammatical Error Correction by Specific Example Selection
LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks
LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts
LLMs + Persona-Plug = Personalized LLMs
LLMs Protégés: Tutoring LLMs with Knowledge Gaps Improves Student Learning Outcome
LLMSR@XLLM25: An Empirical Study of LLM for Structural Reasoning
LLMSR@XLLM25: Integrating Reasoning Prompt Strategies with Structural Prompt Formats for Enhanced Logical Inference
LLMSR@XLLM25: Less is More: Enhancing Structured Multi-Agent Reasoning via Quality-Guided Distillation
LLMSR@XLLM25: SWRV: Empowering Self-Verification of Small Language Models through Step-wise Reasoning and Verification
LLMs syntactically adapt their language use to their conversational partner
LLMs Trust Humans More, That's a Problem! Unveiling and Mitigating the Authority Bias in Retrieval-Augmented Generation
LLM-Symbolic Integration for Robust Temporal Tabular Reasoning
LLMTaxo: Leveraging Large Language Models for Constructing Taxonomy of Factual Claims from Social Media
LLMVoX: Autoregressive Streaming Text-to-Speech Model for Any LLM
LocAgent: Graph-Guided LLM Agents for Code Localization
Localizing and Mitigating Errors in Long-form Question Answering
Locate-and-Focus: Enhancing Terminology Translation in Speech Language Models

« prev Page 46/87 next »