Robuta

https://arxiv.org/abs/2510.04891v1 [2510.04891v1] SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests Abstract page for arXiv paper 2510.04891v1: SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests revealing llm vulnerabilities socially harmful https://is.mpg.de/publications/pandeyetal26 SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests | MPI-IS Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to... revealing llm vulnerabilities socially harmful https://arxiv.org/abs/2510.04891v2 [2510.04891v2] SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests Abstract page for arXiv paper 2510.04891v2: SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests revealing llm vulnerabilities socially harmful