# Safe Guard: an LLM-agent for Real-time Voice-based Hate Speech Detection in Social Virtual Reality

arXiv: https://arxiv.org/abs/2409.15623 · HTML: https://mlsanity.com/paper/2409.15623/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 53 references that are in the map.
- First posted on arXiv 23 Sep 2024.

## Builds on (most cited first, 14 of 14)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [Large Scale Crowdsourcing and Characterization of Twitter Abusive Behavior](https://mlsanity.com/paper/1802.00393/) (2018)
- [Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderation](https://mlsanity.com/paper/2204.11788/) (2022)
- [All You Need is "Love": Evading Hate-speech Detection](https://mlsanity.com/paper/1808.09115/) (2018)
- ["HOT" ChatGPT: The promise of ChatGPT in detecting and discriminating hateful, offensive, and toxic comments on social media](https://mlsanity.com/paper/2304.10619/) (2023)
- [HateMM: A Multi-Modal Dataset for Hate Video Classification](https://mlsanity.com/paper/2305.03915/) (2023)
- [How to Motivate Your Dragon: Teaching Goal-Driven Agents to Speak and Act in Fantasy Worlds](https://mlsanity.com/paper/2010.00685/) (2020)
- [An Investigation of Large Language Models for Real-World Hate Speech Detection](https://mlsanity.com/paper/2401.03346/) (2024)
- [Emotion Based Hate Speech Detection using Multimodal Learning](https://mlsanity.com/paper/2202.06218/) (2022)
- [A Trade-off-centered Framework of Content Moderation](https://mlsanity.com/paper/2206.03450/) (2022)
- [Moderation Challenges in Voice-based Online Communities on Discord](https://mlsanity.com/paper/2101.05258/) (2021)
- [Enabling Contextual Soft Moderation on Social Media through Contrastive Textual Deviation](https://mlsanity.com/paper/2407.20910/) (2024)

## Abstract (arXiv)

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.