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
DEMON at SemEval-2025 Task 10: Fine-tuning LLaMA-3 for Multilingual Entity Framing
Demons in the Detail: On Implementing Load Balancing Loss for Training Specialized Mixture-of-Expert Models
DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling
Demystifying Small Language Models for Edge Deployment
DenseLoRA: Dense Low-Rank Adaptation of Large Language Models
Dense Retrieval with Quantity Comparison Intent
Deontological Keyword Bias: The Impact of Modal Expressions on Normative Judgments of Language Models
DependEval: Benchmarking LLMs for Repository Dependency Understanding
DeRAGEC: Denoising Named Entity Candidates with Synthetic Rationale for ASR Error Correction
Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning
Design Choices for Extending the Context Length of Visual Language Models
Designing and Contextualising Probes for African Languages
DeTAM: Defending LLMs Against Jailbreak Attacks via Targeted Attention Modification
Detecting and Mitigating Challenges in Zero-Shot Video Summarization with Video LLMs
Detecting Bias and Intersectional Bias in Italian Word Embeddings and Language Models
Detecting Child Objectification on Social Media: Challenges in Language Modeling
Detecting Hallucinations in Scientific Claims by Combining Prompting Strategies and Internal State Classification
Detecting Manipulation in Ukrainian Telegram: A Transformer-Based Approach to Technique Classification and Span Identification
Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models
Detecting Sockpuppetry on Wikipedia Using Meta-Learning
Detection of Human and Machine-Authored Fake News in Urdu
Detoxify-IT: An Italian Parallel Dataset for Text Detoxification
Developing a Universal Dependencies Treebank for Ukrainian Parliamentary Speech
Developmentally-plausible Working Memory Shapes a Critical Period for Language Acquisition
DFLOW: Diverse Dialogue Flow Simulation with Large Language Models
D-GEN: Automatic Distractor Generation and Evaluation for Reliable Assessment of Generative Models
Diagnosing Failures in Large Language Models' Answers: Integrating Error Attribution into Evaluation Framework
Dialectal Coverage And Generalization in Arabic Speech Recognition
DIALECTBENCH: An NLP Benchmark for Dialects, Varieties, and Closely-Related Languages
Dialect Normalization using Large Language Models and Morphological Rules
Dialects, Topic Models, and Border Effects: The Rusyn Case
DiaLLMs: EHR-Enhanced Clinical Conversational System for Clinical Test Recommendation and Diagnosis Prediction
Dialogue-RAG: Enhancing Retrieval for LLMs via Node-Linking Utterance Rewriting
Dialogue Systems for Emotional Support via Value Reinforcement
DialUp! Modeling the Language Continuum by Adapting Models to Dialects and Dialects to Models
Dialz: A Python Toolkit for Steering Vectors
Dianchi at SemEval-2025 Task 11: Multilabel Emotion Recognition via Orthogonal Knowledge Distillation
DI-BENCH: Benchmarking Large Language Models on Dependency Inference with Testable Repositories at Scale
DICE-BENCH: Evaluating the Tool-Use Capabilities of Large Language Models in Multi-Round, Multi-Party Dialogues
Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries
Did Translation Models Get More Robust Without Anyone Even Noticing?
DIESEL: A Lightweight Inference-Time Safety Enhancement for Language Models
Different Speech Translation Models Encode and Translate Speaker Gender Differently
DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models
DiffPO: Diffusion-styled Preference Optimization for Inference Time Alignment of Large Language Models
DiffSkip: Differential Layer Skipping in Large Language Models
DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising
Diffusion Directed Acyclic Transformer for Non-Autoregressive Machine Translation
Diffusion Models Through a Global Lens: Are They Culturally Inclusive?
Digest the Knowledge: Large Language Models empowered Message Passing for Knowledge Graph Question Answering

« prev Page 21/87 next »