SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Models
Comments NAACL 2025 Findings
期刊&会议
NAACL
North American Chapter of the Association for Computational Linguistics · 会议 · Natural Language Processing
Tell Me What You Know About Sexism: Expert-LLM Interaction Strategies and Co-Created Definitions for Zero-Shot Sexism Detection
机构 * First Author Affiliation（第一作者机构） ； Second Author Affiliation（第二作者机构）
Comments Accepted and published at Findings of NAACL 2025: cite published version whenever possible
Med-CoDE: Medical Critique based Disagreement Evaluation Framework
机构 * Indraprastha Institute of Information Technology Delhi, India（印度德里印度信息技术研究所） ； National Institute of Informatics, Tokyo, Japan（日本东京信息机构）
Comments 8 pages, 4 figures, NAACL SRW 2025
AI with Emotions: Exploring Emotional Expressions in Large Language Models
机构 * Graduate School of Artificial Intelligence and Science, Rikkyo University（人工智能与科学研究生院，立命馆大学） ； Strategic Digital Business Unit, Mamezou Co., Ltd.（战略数字商务部，麦默株式会社）
Comments 14 pages, 8 figures, accepted to the Natural Language Processing for Digital Humanities (NLP4DH) workshop at NAACL 2025
PROMPTEVALS: A Dataset of Assertions and Guardrails for Custom Production Large Language Model Pipelines
机构 * UC Berkeley（伯克利大学） ； LangChain
Comments Accepted to NAACL 2025 Main Conference
Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert Parallelism Design
机构 * University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Comments NAACL 2025, SAC award for Low-resource Methods for NLP
Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translation
机构 * Digital Twin Institute, Eastern Institute of Technology, Ningbo, China（数字孪生研究所，东部技术研究所，宁波，中国） ； Saarland University（萨尔兰州大学） ； Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））
Comments Accepted at NAACL 2025 Student Research Workshop
Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models
机构 * Nanyang Technological University（南洋理工大学） ； DAMO Academy, Alibaba Group（阿里达摩院） ； Hupan Lab（虎斑实验室） ； National University of Singapore（新加坡国立大学） ； Shanda AI Research Institute（沙达AI研究院）
Comments Accepted to NAACL 2025
Bottom-Up Synthesis of Knowledge-Grounded Task-Oriented Dialogues with Iteratively Self-Refined Prompts
Comments Accepted by NAACL 2025
A Baseline for Self-state Identification and Classification in Mental Health Data: CLPsych 2025 Task
机构 * Cornell University（康奈尔大学）
Comments Accepted to CLPsych Workshop, NAACL 2025
Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation
机构 * College of Computing and Informatics（计算机与信息学院） ； Sungkyunkwan University（全南大学）
Comments NAACL 2025 Findings
Understanding Epistemic Language with a Language-augmented Bayesian Theory of Mind
Comments 23 pages; Published at the Transactions of the Association for Computational Linguistics (TACL); Presented at NAACL 2025
Babysit A Language Model From Scratch: Interactive Language Learning by Trials and Demonstrations
Comments NAACL 2025 (Main) & Workshop on Large Language Models and Cognition @ ICML 2024 (Oral)
Tackling Social Bias against the Poor: A Dataset and Taxonomy on Aporophobia
Comments In Findings of the Association for Computational Linguistics: NAACL 2025
SALAD: Improving Robustness and Generalization through Contrastive Learning with Structure-Aware and LLM-Driven Augmented Data
Comments Accepted to NAACL 2025 main. 15 pages, 4 figures
How Inclusively do LMs Perceive Social and Moral Norms?
Comments Accepted at NAACL 2025 Findings
QAVA: Query-Agnostic Visual Attack to Large Vision-Language Models
Comments Accepted by NAACL 2025 main
LITERA: An LLM Based Approach to Latin-to-English Translation
Comments NAACL Findings
Towards Quantifying Commonsense Reasoning with Mechanistic Insights
Comments Accepted at NAACL 2025; 28 pages (9 pages + 7 pages references + 12 pages appendix)
Enhancing NER Performance in Low-Resource Pakistani Languages using Cross-Lingual Data Augmentation
Comments Accepted to W-NUT 2025 @ NAACL
Voice Interaction With Conversational AI Could Facilitate Thoughtful Reflection and Substantive Revision in Writing
Comments 5 pages; Accepted to Fourth Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2025) at NAACL 2025
CLEAR: Contrasting Textual Feedback with Experts and Amateurs for Reasoning
Comments Accepted at the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), Student Research Workshop (SRW)
EqualizeIR: Mitigating Linguistic Biases in Retrieval Models
Comments NAACL 2025
Journal ref NAACL 2025
S$^2$-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency
Comments Accepted to NAACL 2025 Main
How to Make LLMs Forget: On Reversing In-Context Knowledge Edits
Comments Accepted at NAACL Main 2025
KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs
Comments To be presented at NAACL-HLT, KnowledgeNLP Workshop (2025)
Towards LLMs Robustness to Changes in Prompt Format Styles
Comments NAACL Student Research Workshop (SRW) 2025
A Diverse and Effective Retrieval-Based Debt Collection System with Expert Knowledge
Comments Accepted by NAACL 2025, Industry Track
Explainable ICD Coding via Entity Linking
Comments Accepted at CL4Health at NAACL 2025
STEP: Staged Parameter-Efficient Pre-training for Large Language Models
Comments Accepted to NAACL 2025 Main
