Diverse Preference Learning for Capabilities and Alignment

Documenti analoghi

• Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optimize Misaligned Biases
  di: Hahm, Dongyoon, et al.
  Pubblicazione: (2026)
• Improving Influence-based Instruction Tuning Data Selection for Balanced Learning of Diverse Capabilities
  di: Dai, Qirun, et al.
  Pubblicazione: (2025)
• ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
  di: Bian, Zhipeng, et al.
  Pubblicazione: (2026)
• RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences
  di: Zhou, Yangyang, et al.
  Pubblicazione: (2026)
• Cross-lingual Human-Preference Alignment for Neural Machine Translation with Direct Quality Optimization
  di: Uhlig, Kaden, et al.
  Pubblicazione: (2024)