Exposing Long-Tail Safety Failures in Large Language Models through Efficient Diverse Response Sampling

Ähnliche Einträge

• Innocence in the Crossfire: Roles of Skip Connections in Jailbreaking Visual Language Models
  von: Nandi, Palash, et al.
  Veröffentlicht: (2025)
• SABER: Uncovering Vulnerabilities in Safety Alignment via Cross-Layer Residual Connection
  von: Joshi, Maithili, et al.
  Veröffentlicht: (2025)
• SAFE-MEME: Structured Reasoning Framework for Robust Hate Speech Detection in Memes
  von: Nandi, Palash, et al.
  Veröffentlicht: (2024)
• Recent Advances in Hate Speech Moderation: Multimodality and the Role of Large Models
  von: Hee, Ming Shan, et al.
  Veröffentlicht: (2024)
• First Finish Search: Efficient Test-Time Scaling in Large Language Models
  von: Agarwal, Aradhye, et al.
  Veröffentlicht: (2025)