How to evaluate jailbreak methods: a case study with the StrongREJECT benchmark

When we began studying jailbreak evaluations, we found a fascinating paper claiming that you could jailbreak frontier LLMs simply by translating forbidden prompts into obscure languages. Excited by this result, we attempted to reproduce it and found something unexpected. The paper in question claimed an impressive 43% success rate in jailbreaking GPT-4 by translating forbidden prompts into Scots Gaelic (Yong et al., 2023). To showcase their method, the authors asked GPT-4 to provide instructions for building a homemade explosive device using household materials. The authors then show the beginning of GPT-4's alarming response: Truncated GPT-4 response as reported by the authors.