4 citations · 8 across the 4 of their papers we have counts for
4 papers
A Red Teaming Roadmap Towards System-Level Safety
Zifan Wang, Christina Q. Knight, Jeremy Kritz +2
Large Language Model (LLM) safeguards, which implement request refusals, have become a widely adopted mitigation strategy against misuse. At the intersection of adversarial machine…
Jailbreaking to Jailbreak
Jeremy Kritz, Vaughn Robinson, Robert Vacareanu +7
Large Language Models (LLMs) can be used to red team other models (e.g. jailbreaking) to elicit harmful contents. While prior works commonly employ open-weight models or private un…
MultiChallenge: A Realistic Multi-Turn Conversation Evaluation Benchmark Challenging to Frontier LLMs
Ved Sirdeshmukh, Kaustubh Deshpande, Johannes Mols +7
We present MultiChallenge, a pioneering benchmark evaluating large language models (LLMs) on conducting multi-turn conversations with human users, a crucial yet underexamined capab…
LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet
Nathaniel Li, Ziwen Han, Ian Steneker +6
Recent large language model (LLM) defenses have greatly improved models' ability to refuse harmful queries, even when adversarially attacked. However, LLM defenses are primarily ev…