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
Abstract
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 …..
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers1
Ask how each one uses itBuilds on10
- Large Language Models are Zero-Shot ReasonersTakeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo et al.NeurIPS 2022 · 8,168 citations
- Self-Consistency Improves Chain of Thought Reasoning in Language ModelsXuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V. Le et al.ICLR 2023 · 681 citations
- Encouraging Divergent Thinking in Large Language Models through Multi-Agent DebateTian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang et al.EMNLP 2024 · 177 citations
- 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 · 145 citations
- Theory of Mind for Multi-Agent Collaboration via Large Language ModelsHuao Li, Yu Quan Chong, Simon Stepputtis, Joseph Campbell et al.EMNLP 2023 · 57 citations
Related papers
- Analyze-Compose-Execute: A Dynamic Dialogue Framework for Multi-Agent DebateWenyuan Gu, Haowen Wang, Jiale Han, Xiang Li et al.AAAI 2026
- MAD-Logic: Multi-Agent Debate Enhances Symbolic Translation and ReasoningHaocheng Yang, Fengxiang Cheng, Tianjun Yao, Mengyue Yang et al.ICLR 2026
- M-MAD: Multidimensional Multi-Agent Debate for Advanced Machine Translation EvaluationZhaopeng Feng, Jiayuan Su, Jiamei Zheng, Jiahan Ren et al.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 · 93 citations
