Bi-Factorial Preference Optimization: Balancing Safety-Helpfulness in Language Models

Documenti analoghi

• Universal In-Context Approximation By Prompting Fully Recurrent Models
  di: Petrov, Aleksandar, et al.
  Pubblicazione: (2024)
• Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
  di: Hammoud, Hasan Abed Al Kader, et al.
  Pubblicazione: (2024)
• No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages
  di: Mohamed, Youssef, et al.
  Pubblicazione: (2024)
• Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning
  di: Alssum, Lama, et al.
  Pubblicazione: (2025)
• Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
  di: Zhang, Wenxuan, et al.
  Pubblicazione: (2024)