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
BlockPruner: Fine-grained Pruning for Large Language Models
Blue-haired, misandriche, rabiata: Tracing the Connotation of ‘Feminist(s)’ Across Time, Languages and Domains
BlueToad at SemEval-2025 Task 3: Using Question-Answering-Based Language Models to Extract Hallucinations from Machine-Generated Text
BMIKE-53: Investigating Cross-Lingual Knowledge Editing with In-Context Learning
Bone Soups: A Seek-and-Soup Model Merging Approach for Controllable Multi-Objective Generation
BOOKCOREF: Coreference Resolution at Book Scale
BOOKWORLD: From Novels to Interactive Agent Societies for Story Creation
Boost, Disentangle, and Customize: A Robust System2-to-System1 Pipeline for Code Generation
Boosting LLM's Molecular Structure Elucidation with Knowledge Enhanced Tree Search Reasoning
Boosting LLM Translation Skills without General Ability Loss via Rationale Distillation
Boosting Long-Context Information Seeking via Query-Guided Activation Refilling
Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA
Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data
Bootstrapping UMRs from Universal Dependencies for Scalable Multilingual Annotation
BOSE: A Systematic Evaluation Method Optimized for Base Models
BottleHumor: Self-Informed Humor Explanation using the Information Bottleneck Principle
BPP-Search: Enhancing Tree of Thought Reasoning for Mathematical Modeling Problem Solving
BQA: Body Language Question Answering Dataset for Video Large Language Models
BrainECHO: Semantic Brain Signal Decoding through Vector-Quantized Spectrogram Reconstruction for Whisper-Enhanced Text Generation
Breaking the Ceiling: Exploring the Potential of Jailbreak Attacks through Expanding Strategy Space
Breaking the Reasoning Barrier A Survey on LLM Complex Reasoning through the Lens of Self-Evolution
Breaking the Transcription Bottleneck: Fine-tuning ASR Models for Extremely Low-Resource Fieldwork Languages
Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms
Brevity is the soul of sustainability: Characterizing LLM response lengths
Bridge-Coder: Transferring Model Capabilities from High-Resource to Low-Resource Programming Language
Bridging AI and Carbon Capture: A Dataset for LLMs in Ionic Liquids and CBE Research
Bridging Intuitive Associations and Deliberate Recall: Empowering LLM Personal Assistant with Graph-Structured Long-term Memory
Bridging Relevance and Reasoning: Rationale Distillation in Retrieval-Augmented Generation
Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach
Bridging the Data Gap in Financial Sentiment: LLM-Driven Augmentation
Bridging the Digital Divide: Empowering Elderly Smartphone Users with Intelligent and Human-Centered Design in Agemate
Bridging the Embodiment Gap in Agricultural Knowledge Representation for Language Models
Bridging the Language Gaps in Large Language Models with Inference-Time Cross-Lingual Intervention
Bridging the LLM Accessibility Divide? Performance, Fairness, and Cost of Closed versus Open LLMs for Automated Essay Scoring
Bridging the Socioeconomic Gap in Education: A Hybrid AI and Human Annotation Approach
BridG MT: Enhancing LLMs' Machine Translation Capabilities with Sentence Bridging and Gradual MT
BriefMe: A Legal NLP Benchmark for Assisting with Legal Briefs
BrightCookies at SemEval-2025 Task 9: Exploring Data Augmentation for Food Hazard Classification
BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages
Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion
Browsing Like Human: A Multimodal Web Agent with Experiential Fast-and-Slow Thinking
Browsing Lost Unformed Recollections: A Benchmark for Tip-of-the-Tongue Search and Reasoning
Building a Functional Machine Translation Corpus for Kpelle
Building a Long Text Privacy Policy Corpus with Multi-Class Labels
Building A Proof-Oriented Programmer That Is 64% Better Than GPT-4o Under Data Scarcity
Building Better: Avoiding Pitfalls in Developing Language Resources when Data is Scarce
Building Japanese Creativity Benchmarks and Applying them to Enhance LLM Creativity
BUINUS at IWSLT: Evaluating the Impact of Data Augmentation and QLoRA-based Fine-Tuning for Maltese to English Speech Translation
Burn After Reading: Do Multimodal Large Language Models Truly Capture Order of Events in Image Sequences?
Bypassing LLM Guardrails: An Empirical Analysis of Evasion Attacks against Prompt Injection and Jailbreak Detection Systems

« prev Page 11/87 next »