@inproceedings{zhang-etal-2025-madawsd,
    title = "{MADAWSD}: Multi-Agent Debate Framework for Adversarial Word Sense Disambiguation",
    author = "Zhang, Kaiyuan  and
      Liu, Qian  and
      Zhang, Luyang  and
      Zheng, Chaoqun  and
      Li, Shuaimin  and
      Xu, Bing  and
      Yang, Muyun  and
      Qiao, Xinxiao  and
      Lu, Wenpeng",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1134/",
    pages = "22294--22313",
    ISBN = "979-8-89176-332-6",
    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."
}