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
Behavioral Analysis of Information Salience in Large Language Models
BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models
Behavioural vs. Representational Systematicity in End-to-End Models: An Opinionated Survey
Behind Closed Words: Creating and Investigating the forePLay Annotated Dataset for Polish Erotic Discourse
BelarusianGLUE: Towards a Natural Language Understanding Benchmark for Belarusian
Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines
BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question Answering
Bemba Speech Translation: Exploring a Low-Resource African Language
Benchmarking and Improving Large Vision-Language Models for Fundamental Visual Graph Understanding and Reasoning
Benchmarking LLMs and LLM-based Agents in Practical Vulnerability Detection for Code Repositories
Benchmarking Long-Context Language Models on Long Code Understanding
Benchmarking Multimodal Models for Ukrainian Language Understanding Across Academic and Cultural Domains
Benchmarking Multi-National Value Alignment for Large Language Models
Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models
Benchmarking query-conditioned natural language inference
Benchmarking Table Extraction: Multimodal LLMs vs Traditional OCR
Benchmarking the Benchmarks: Reproducing Climate-Related NLP Tasks
Benchmarking zero-shot biomedical relation triplet extraction across language model architectures
BenNumEval: A Benchmark to Assess LLMs' Numerical Reasoning Capabilities in Bengali
BERTastic at SemEval-2025 Task 10: State-of-the-Art Accuracy in Coarse-Grained Entity Framing for Hindi News
BERT-like Models for Slavic Morpheme Segmentation
BESSTIE: A Benchmark for Sentiment and Sarcasm Classification for Varieties of English
Better Embeddings with Coupled Adam
Better Process Supervision with Bi-directional Rewarding Signals
Better Red Teaming via Searching with Large Language Model
Between Circuits and Chomsky: Pre-pretraining on Formal Languages Imparts Linguistic Biases
Between Hetero-Fatalism and Dark Femininity: Discussions of Relationships, Sex, and Men in the Femosphere
Beware of Your Po! Measuring and Mitigating AI Safety Risks in Role-Play Fine-Tuning of LLMs
Beyond Accuracy: Revisiting Out-of-Distribution Generalization in NLI Models
Beyond Browsing: API-Based Web Agents
Beyond Citations: Integrating Finding-Based Relations for Improved Biomedical Article Representations
Beyond cognacy
Beyond Completion: A Foundation Model for General Knowledge Graph Reasoning
Beyond Context to Cognitive Appraisal: Emotion Reasoning as a Theory of Mind Benchmark for Large Language Models
Beyond Decoder-only: Large Language Models Can be Good Encoders for Machine Translation
Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions
Beyond Dialogue: A Profile-Dialogue Alignment Framework Towards General Role-Playing Language Model
Beyond Facts: Evaluating Intent Hallucination in Large Language Models
Beyond Factual Accuracy: Evaluating Coverage of Diverse Factual Information in Long-form Text Generation
Beyond Frameworks: Unpacking Collaboration Strategies in Multi-Agent Systems
Beyond Generalization :Evaluating Multilingual LLMs for Yorùbá Animal Health Translation
Beyond Generation: Leveraging LLM Creativity to Overcome Label Bias in Classification
Beyond In-Context Learning: Aligning Long-form Generation of Large Language Models via Task-Inherent Attribute Guidelines
Beyond instruction-conditioning, MoTE: Mixture of Task Experts for Multi-task Embedding Models
Beyond Linear Digital Reading: An LLM-Powered Concept Mapping Approach for Reducing Cognitive Load
Beyond Logits: Aligning Feature Dynamics for Effective Knowledge Distillation
Beyond Negative Stereotypes - Non-Negative Abusive Utterances about Identity Groups and Their Semantic Variants
Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization
Beyond Numeric Rewards: In-Context Dueling Bandits with LLM Agents
Beyond One-Size-Fits-All: Tailored Benchmarks for Efficient Evaluation

« prev Page 9/87 next »