arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.09342cs.CLcs.AI
收藏

通过社区驱动的多智能体框架改进隐式仇恨言论检测

Improving Implicit Hate Speech Detection via a Community-Driven Multi-Agent Framework

Warsaw University of Technology(华沙技术大学)

Ewelina Gajewska, Katarzyna Budzynska, Jarosław A Chudziak

AI总结:

本文提出一种社区驱动的多智能体框架,通过整合社会文化背景提升隐式仇恨言论检测的准确性和公平性。

摘要:

本文提出了一种上下文化的隐式仇恨言论检测框架,实现为由中央调解员智能体和动态构建的社区智能体组成的多智能体系统。我们的方法明确整合了公开可用的知识来源中的社会文化背景,使身份感知的调解能够超越最先进的提示方法(零样本提示、少样本提示、思维链提示)和其他替代方法,在具有挑战性的ToxiGen数据集上取得优势。我们通过将平衡准确率作为分类公平性的核心指标来增强性能评估的技术严谨性,该指标考虑了真阳性率和真阴性率之间的权衡。我们证明了我们的社区驱动咨询框架在所有目标群体中显著提高了分类准确性和公平性。

英文摘要:

This work proposes a contextualised detection framework for implicitly hateful speech, implemented as a multi-agent system comprising a central Moderator Agent and dynamically constructed Community Agents representing specific demographic groups. Our approach explicitly integrates socio-cultural context from publicly available knowledge sources, enabling identity-aware moderation that surpasses state-of-the-art prompting methods (zero-shot prompting, few-shot prompting, chain-of-thought prompting) and alternative approaches on a challenging ToxiGen dataset. We enhance the technical rigour of performance evaluation by incorporating balanced accuracy as a central metric of classification fairness that accounts for the trade-off between true positive and true negative rates. We demonstrate that our community-driven consultative framework significantly improves both classification accuracy and fairness across all target groups.

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。

↑