TurQUaz at CheckThat! 2025：用于科学网络话语检测的辩论大语言模型
TurQUaz at CheckThat! 2025: Debating Large Language Models for Scientific Web Discourse Detection
AI总结：
本文为 CheckThat! 2025 科学网络话语检测任务提出一种模拟多 LLM 结构化学术讨论的委员会辩论方法，该方法在检测科学研究引用方面排名第一。
摘要：
在本文中，我们介绍了为 CheckThat! 2025 的科学网络话语检测任务（Task 4a）所开发的工作。我们提出了一种新颖的委员会辩论方法，该方法模拟多个大语言模型（LLMs）之间的结构化学术讨论，以识别给定推文是否包含： 科学声明， 对科学研究的引用，或 对科学实体的提及。我们探索了三种辩论方法：i) 单次辩论，两个 LLM 为对立立场辩论，第三个作为裁判；ii) 团队辩论，多个模型在辩论各方内协作；iii) 委员会辩论，多个专家模型共同审议以达成共识，由主持人模型主持。我们选择委员会辩论作为主要模型，因为它在开发测试集中优于其他方法。尽管我们提出的方法在识别科学声明（10个中第8）或科学实体提及（10个中第9）方面排名不高，但它在检测科学研究引用方面排名第一。
英文摘要：
In this paper, we present our work developed for the scientific web discourse detection task (Task 4a) of CheckThat! 2025. We propose a novel council debate method that simulates structured academic discussions among multiple large language models (LLMs) to identify whether a given tweet contains (i) a scientific claim, (ii) a reference to a scientific study, or (iii) mentions of scientific entities. We explore three debating methods: i) single debate, where two LLMs argue for opposing positions while a third acts as a judge; ii) team debate, in which multiple models collaborate within each side of the debate; and iii) council debate, where multiple expert models deliberate together to reach a consensus, moderated by a chairperson model. We choose council debate as our primary model as it outperforms others in the development test set. Although our proposed method did not rank highly for identifying scientific claims (8th out of 10) or mentions of scientific entities (9th out of 10), it ranked first in detecting references to scientific studies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
