RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
arxiv.org · 5,980 words · saved by 1 readers
N/A
RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content Zhuowen Yuan 1 Zidi Xiong 1 Yi Zeng 2 Ning Yu 3 Ruoxi Jia 2 Dawn Song 4 Bo Li 1 5 Harmful Instruction Abstract with Jailbreak Attacks…
saved by
related reading
- Legilimens: Practical and Unified Content Moderation forLarge Language Model Servicesarxiv.org
- 2312.06674arxiv.org
- [2502.05209] Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilitiesarxiv.org
- LLM-Mod: Can Large Language Models Assist Content Moderation?koustuv.com
- 2025.naacl-long.441.pdfaclanthology.org
- Modifying LLM Beliefs with Synthetic Document Finetuningalignment.anthropic.com
- 2408.12798arxiv.org
- [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
- Large Language Diffusion Modelsarxiv.org
- Refusal in LLMs is mediated by a single direction — LessWronglesswrong.com
- Language Models are Elasticaclanthology.org
- Poisoning Attacks on LLMs Require a Near-constant Number of Poison Samplesarxiv.org