ProSocialAlign: Preference Conditioned Test Time Alignment in Language Models

Documenti analoghi

• MemeSense: An Adaptive In-Context Framework for Social Commonsense Driven Meme Moderation
  di: Adak, Sayantan, et al.
  Pubblicazione: (2025)
• Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
  di: Banerjee, Somnath, et al.
  Pubblicazione: (2025)
• SafeInfer: Context Adaptive Decoding Time Safety Alignment for Large Language Models
  di: Banerjee, Somnath, et al.
  Pubblicazione: (2024)
• How (un)ethical are instruction-centric responses of LLMs? Unveiling the vulnerabilities of safety guardrails to harmful queries
  di: Banerjee, Somnath, et al.
  Pubblicazione: (2024)
• Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
  di: Hazra, Rima, et al.
  Pubblicazione: (2024)