MADAWSD: Multi-Agent Debate Framework for Adversarial Word Sense Disambiguation
Kaiyuan Zhang, Qian Liu, Luyang Zhang, Chaoqun Zheng, Shuaimin Li, Bing Xu, Muyun Yang, Xinxiao Qiao, Wenpeng Lu
摘要
Word sense disambiguation (WSD) is a fundamental yet challenging task in natural language processing. In recent years, the advent of large language models (LLMs) has led to significant advancements in regular WSD tasks. However, most existing LLMs face two major issues that hinder their performance in WSD. Firstly, these models are often prone to misclassifying the correct meaning of an ambiguous word when confronted with contexts containing adversarial information. Secondly, there is a lack of sufficient adversarial WSD datasets, which severely limits the development and evaluation of adversarial WSD systems. To address these gaps, we propose a novel Multi-Agent Debate framework for Adversarial Word Sense Disambiguation (MADAWSD). The MADAWSD framework simulates a real-world debate environment where multiple agent roles, namely, the Debater, Moderator, Consensus-seeker, and Judge, engage in discussions about ambiguous words in the context of adversarial information. Through a collaborative mechanism among these agents, it achieves accurate WSD. Additionally, a novel dataset for Chinese adversarial WSD has been constructed, focusing on improving and evaluating the performance of WSD models in the Chinese language. Extensive experiments on both English and Chinese adversarial WSD datasets demonstrate that MADAWSD can seamlessly integrate with existing LLMs and significantly enhance their performance, showcasing broad generality and outstanding effectiveness. 1 * Corresponding author 1 The full source code and datasets are publicly available at https://github.com/KaiyCheung/MADAWSD . Context: Apple 's employees are eating fruits. Debate Topic: In this sentence: 'Apple 's employees are eating fruits.', classify the occurrence of the word 'apple' for "fruit" or for "company". Output the reason before output the answer. For example: Reason: Give your reasons. Answer: "fruit " or "company" Reason: The word …, So I think … Answer: fruit Reason: I disagree your opinion… because ….. So …..
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper1
问问它们各自怎么用它它引用的顶会 Paper10
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo 等NeurIPS 2022 · 被引用 8,168 次
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le 等ICLR 2023 · 被引用 681 次
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent DebateTian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang 等EMNLP 2024 · 被引用 177 次
- Breaking Through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph InformationMichele Bevilacqua, Roberto NavigliACL 2020 · 被引用 145 次
- Theory of Mind for Multi-Agent Collaboration via Large Language ModelsHuao Li, Yu Quan Chong, Simon Stepputtis, Joseph Campbell 等EMNLP 2023 · 被引用 57 次
相关 Paper
- Analyze-Compose-Execute: A Dynamic Dialogue Framework for Multi-Agent DebateWenyuan Gu, Haowen Wang, Jiale Han, Xiang Li 等AAAI 2026
- MAD-Logic: Multi-Agent Debate Enhances Symbolic Translation and ReasoningHaocheng Yang, Fengxiang Cheng, Tianjun Yao, Mengyue Yang 等ICLR 2026
- M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation EvaluationZhaopeng Feng, Jiayuan Su, Jiamei Zheng, Jiahan Ren 等ACL 2025
- Towards General-Domain Word Sense Disambiguation: Distilling Large Language Model into Compact DisambiguatorLiqiang Ming, Sheng-hua Zhong, Yuncong LiEMNLP 2025
- Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?Hyeong Kyu Choi, Xiaojin Zhu, Sharon LiNeurIPS 2025 · 被引用 93 次
