用知识图谱提升大模型仇恨言论检测准确率，减少误判。
Enhancing LLM-based Hatred and Toxicity Detection with Meta-Toxic Knowledge Graph
- 构建元毒性知识图谱，通过三步流程提取毒害信息。
- 检索图谱知识后，误报率下降，整体检测效果提升。
- 适合需要精准识别毒害内容的平台与研究者使用。
社交媒体快速发展引发了在线内容毒害问题的广泛关注。当大型语言模型（LLMs）用于毒性检测时，面临两大挑战：一是缺乏领域特定毒害知识导致漏检；二是模型对毒害言论过度敏感引发误报，限制言论自由。为此，我们提出一种新方法MetaTox，利用元毒性知识图谱的图搜索来增强仇恨与毒性检测。首先，基于毒害基准数据集，通过三步流程构建全面的元毒性知识图谱；其次，通过检索与排序过程查询图谱，补充精准相关的毒害知识。在多个数据集上的大量实验与深入案例分析表明，MetaTox显著降低误报率，同时提升整体毒性检测性能。代码已公开于 https://github.com/YiboZhao624/MetaTox。
原文摘要 · Abstract (English)
The rapid growth of social media platforms has raised significant concerns regarding online content toxicity. When Large Language Models (LLMs) are used for toxicity detection, two key challenges emerge: 1) the absence of domain-specific toxic knowledge leads to false negatives; 2) the excessive sensitivity of LLMs to toxic speech results in false positives, limiting freedom of speech. To address these issues, we propose a novel method called MetaTox, leveraging graph search on a meta-toxic knowledge graph to enhance hatred and toxicity detection. First, we construct a comprehensive meta-toxic knowledge graph by utilizing LLMs to extract toxic information through a three-step pipeline, with toxic benchmark datasets serving as corpora. Second, we query the graph via retrieval and ranking processes to supplement accurate, relevant toxic knowledge. Extensive experiments and in-depth case studies across multiple datasets demonstrate that our MetaTox significantly decreases the false positive rate while boosting overall toxicity detection performance. Our code is available at https://github.com/YiboZhao624/MetaTox.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。