用大模型实时识别社交虚拟现实中的语音仇恨言论。
Safe Guard: an LLM-agent for Real-time Voice-based Hate Speech Detection in Social Virtual Reality
- 结合GPT与音频特征提取，实现语音互动的实时检测。
- 相比现有方法，显著降低误报率，提升检测准确性。
- 为虚拟空间安全治理提供可扩展的大模型解决方案。
本文提出 Safe Guard，一个用于社交虚拟现实（VRChat）中基于语音交互的仇恨言论检测的 LLM-agent。系统利用 OpenAI GPT 与音频特征提取技术，实现对实时语音内容的高效分析。实验表明，该方法在检测仇恨言论方面具备良好性能，同时相比现有方案显著降低了误报率。研究验证了基于大模型的智能代理在构建更安全虚拟环境中的潜力，为未来 LLM 驱动的内容治理技术发展奠定基础。
原文摘要 · Abstract (English)
In this paper, we present Safe Guard, an LLM-agent for the detection of hate speech in voice-based interactions in social VR (VRChat). Our system leverages Open AI GPT and audio feature extraction for real-time voice interactions. We contribute a system design and evaluation of the system that demonstrates the capability of our approach in detecting hate speech, and reducing false positives compared to currently available approaches. Our results indicate the potential of LLM-based agents in creating safer virtual environments and set the groundwork for further advancements in LLM-driven moderation approaches.
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。