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
HyKGE: A Hypothesis Knowledge Graph Enhanced RAG Framework for Accurate and Reliable Medical LLMs Responses
HyperCRS: Hypergraph-Aware Multi-Grained Preference Learning to Burst Filter Bubbles in Conversational Recommendation System
HyperFM: Fact-Centric Multimodal Fusion for Link Prediction over Hyper-Relational Knowledge Graphs
HYPEROFA: Expanding LLM Vocabulary to New Languages via Hypernetwork-Based Embedding Initialization
Hypothetical Documents or Knowledge Leakage? Rethinking LLM-based Query Expansion
I0T: Embedding Standardization Method Towards Zero Modality Gap
I2R-NLP at SemEval-2025 Task 8: Question Answering on Tabular Data
iai_MSU at SemEval-2025 Task-3: Mu-SHROOM, the Multilingual Shared-task on Hallucinations and Related Observable Overgeneration Mistakes in English
IALab UC at BEA 2025 Shared Task: LLM-Powered Expert Pedagogical Feature Extraction
IAM: Efficient Inference through Attention Mapping between Different-scale LLMs
IASBS at SemEval-2025 Task 11: Ensembling Transformers for Bridging the Gap in Text-Based Emotion Detection
ICLE-RC: International Corpus of Learner English for Relative Clauses
ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
Identifying Cellular Niches in Spatial Transcriptomics: An Investigation into the Capabilities of Large Language Models
Identifying Filled Pauses in Speech Across South and West Slavic Languages
Identifying Open Challenges in Language Identification
Identifying Reliable Evaluation Metrics for Scientific Text Revision
IEGPS-CSIC at SemEval-2025 Task 11: BERT-based approach for Multi-label Emotion Detection in English and Russian texts
If Attention Serves as a Cognitive Model of Human Memory Retrieval, What is the Plausible Memory Representation?
If Eleanor Rigby Had Met ChatGPT: A Study on Loneliness in a Post-LLM World
IIITH-BUT system for IWSLT 2025 low-resource Bhojpuri to Hindi speech translation
Illuminating Logical Fallacies with the CAMPFIRE Corpus
iLostTheCode at SemEval-2025 Task 10: Bottom-up Multilevel Classification of Narrative Taxonomies
Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models
IMOL: Incomplete-Modality-Tolerant Learning for Multi-Domain Fake News Video Detection
iMOVE : Instance-Motion-Aware Video Understanding
IMPARA-GED: Grammatical Error Detection is Boosting Reference-free Grammatical Error Quality Estimator
Impartial Multi-task Representation Learning via Variance-invariant Probabilistic Decoding
ImPart: Importance-Aware Delta-Sparsification for Improved Model Compression and Merging in LLMs
Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment
Implicit Hate Target Span Detection in Zero- and Few-Shot Settings with Selective Sub-Billion Parameter Models
Implicit Reasoning in Transformers is Reasoning through Shortcuts
ImpliHateVid: A Benchmark Dataset and Two-stage Contrastive Learning Framework for Implicit Hate Speech Detection in Videos
Improved Unbiased Watermark for Large Language Models
Improve Language Model and Brain Alignment via Associative Memory
Improve Rule Retrieval and Reasoning with Self-Induction and Relevance ReEstimate
Improve Safety Training of Large Language Models with Safety-Critical Singular Vectors Localization
Improve Vision Language Model Chain-of-thought Reasoning
Improving AI assistants embedded in short e-learning courses with limited textual content
Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-Judge
Improving Barrett’s Oesophagus Surveillance Scheduling with Large Language Models: A Structured Extraction Approach
Improving Causal Interventions in Amnesic Probing with Mean Projection or LEACE
Improving Chain-of-Thought Reasoning via Quasi-Symbolic Abstractions
Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization
Improving Continual Pre-training Through Seamless Data Packing
Improving Dialogue Discourse Parsing through Discourse-aware Utterance Clarification
Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples
Improving Efficiency in Large Language Models via Extendable Block Floating Point Representation
Improving Explainability of Sentence-level Metrics via Edit-level Attribution for Grammatical Error Correction
Improving Factuality with Explicit Working Memory

« prev Page 38/87 next »