WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models

Documenti analoghi

• WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
  di: Han, Seungju, et al.
  Pubblicazione: (2024)
• What Makes it Ok to Set a Fire? Iterative Self-distillation of Contexts and Rationales for Disambiguating Defeasible Social and Moral Situations
  di: Rao, Kavel, et al.
  Pubblicazione: (2023)
• AI as Humanity's Salieri: Quantifying Linguistic Creativity of Language Models via Systematic Attribution of Machine Text against Web Text
  di: Lu, Ximing, et al.
  Pubblicazione: (2024)
• WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild
  di: Lin, Bill Yuchen, et al.
  Pubblicazione: (2024)
• Multi-Attribute Constraint Satisfaction via Language Model Rewriting
  di: Baheti, Ashutosh, et al.
  Pubblicazione: (2024)