Login / Signup

WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs.

Seungju HanKavel RaoAllyson EttingerLiwei JiangBill Yuchen LinNathan LambertYejin ChoiNouha Dziri
Published in: CoRR (2024)
Keyphrases
  • decision support
  • genetic algorithm
  • decision making
  • open systems
  • user friendly
  • risk management
  • software tools
  • computational tools
  • application programming interfaces