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
Semantic alignment in hyperbolic space for fine-grained emotion classification
Semantic Aware Linear Transfer by Recycling Pre-trained Language Models for Cross-lingual Transfer
SemanticCamo: Jailbreaking Large Language Models through Semantic Camouflage
Semantic Convergence: Investigating Shared Representations Across Scaled LLMs
Semantic-Eval : A Semantic Comprehension Evaluation Framework for Large Language Models Generation without Training
Semantic Evaluation of Multilingual Data-to-Text Generation via NLI Fine-Tuning: Precision, Recall and F1 scores
Semantic Exploration with Adaptive Gating for Efficient Problem Solving with Language Models
Semantic Frame Induction from a Real-World Corpus
Semantic Outlier Removal with Embedding Models and LLMs
Semantics-aware prompting for translating NOtices To AirMen
Semantic Topology: a New Perspective for Communication Style Characterization
SemEval 2025 Task 10: Multilingual Characterization and Extraction of Narratives from Online News
SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection
SemEval-2025 Task 1: AdMIRe - Advancing Multimodal Idiomaticity Representation
SemEval-2025 Task 2: Entity-Aware Machine Translation
SemEval-2025 Task 3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes
SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models
SemEval-2025 Task 5: LLMs4Subjects - LLM-based Automated Subject Tagging for a National Technical Library’s Open-Access Catalog
SemEval-2025 Task 6: Multinational, Multilingual, Multi-Industry Promise Verification
SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval
SemEval-2025 Task 8: Question Answering over Tabular Data
SemEval-2025 Task 9: The Food Hazard Detection Challenge
SemQA: Evaluating Evidence with Question Embeddings and Answer Entailment for Fact Verification
Sensitive Content Classification in Social Media: A Holistic Resource and Evaluation
Sens-Merging: Sensitivity-Guided Parameter Balancing for Merging Large Language Models
Sentimental Image Generation for Aspect-based Sentiment Analysis
SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods
SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection
Separate the Wheat from the Chaff: A Post-Hoc Approach to Safety Re-Alignment for Fine-Tuned Language Models
Separating Tongue from Thought: Activation Patching Reveals Language-Agnostic Concept Representations in Transformers
SEPSIS: I Can Catch Your Lies -- A New Paradigm for Deception Detection
SeqMMR: Sequential Model Merging and LLM Routing for Enhanced Batched Sequential Knowledge Editing
SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation
SequentialBreak: Large Language Models Can be Fooled by Embedding Jailbreak Prompts into Sequential Prompt Chains
Serial Lifelong Editing via Mixture of Knowledge Experts
Serial Position Effects of Large Language Models
SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs?
SGDPO: Self-Guided Direct Preference Optimization for Language Model Alignment
SGIC: A Self-Guided Iterative Calibration Framework for RAG
SHA256 at SemEval-2025 Task 4: Selective Amnesia – Constrained Unlearning for Large Language Models via Knowledge Isolation
Shadow-Activated Backdoor Attacks on Multimodal Large Language Models
Shallow Preference Signals: Large Language Model Aligns Even Better with Truncated Data?
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models
SHARE: An SLM-based Hierarchical Action CorREction Assistant for Text-to-SQL
Shared Task at Biolaysumm2025 : Extract then summarize approach Augmented with UMLS based Definition Retrieval for Lay Summary generation.
SHARE: Shared Memory-Aware Open-Domain Long-Term Dialogue Dataset Constructed from Movie Script
Sharper and Faster mean Better: Towards More Efficient Vision-Language Model for Hour-scale Long Video Understanding
SHARP: Unlocking Interactive Hallucination via Stance Transfer in Role-Playing LLMs
Sheep's Skin, Wolf's Deeds: Are LLMs Ready for Metaphorical Implicit Hate Speech?
SheffieldGATE at SemEval-2025 Task 2: Multi-Stage Reasoning with Knowledge Fusion for Entity Translation

« prev Page 69/87 next »