Litcius/Paper detail

Jailbroken: How Does LLM Safety Training Fail?

Nika Haghtalab, Jacob Steinhardt, Alexander Wei

202335 citationsDOI

Topics & Concepts

Occupational Health and Safety ResearchPatient Safety and Medication ErrorsChemical Safety and Risk Management
Jailbroken: How Does LLM Safety Training Fail? | Litcius