Immune: Improving Safety Against Jailbreaks in Multi-modal LLMs via Inference-Time Alignment

Documenti analoghi

• Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
  di: Ghosal, Soumya Suvra, et al.
  Pubblicazione: (2026)
• Transfer Q Star: Principled Decoding for LLM Alignment
  di: Chakraborty, Souradip, et al.
  Pubblicazione: (2024)
• Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
  di: Chehade, Mohamad, et al.
  Pubblicazione: (2025)
• Does Thinking More always Help? Mirage of Test-Time Scaling in Reasoning Models
  di: Ghosal, Soumya Suvra, et al.
  Pubblicazione: (2025)
• LIAR: Leveraging Inference Time Alignment (Best-of-N) to Jailbreak LLMs in Seconds
  di: Beetham, James, et al.
  Pubblicazione: (2024)