On the Robustness of Reward Models for Language Model Alignment

Documenti analoghi

• Cross-lingual Transfer of Reward Models in Multilingual Alignment
  di: Hong, Jiwoo, et al.
  Pubblicazione: (2024)
• ORPO: Monolithic Preference Optimization without Reference Model
  di: Hong, Jiwoo, et al.
  Pubblicazione: (2024)
• Rethinking the Role of Proxy Rewards in Language Model Alignment
  di: Kim, Sungdong, et al.
  Pubblicazione: (2024)
• AlphaPO: Reward Shape Matters for LLM Alignment
  di: Gupta, Aman, et al.
  Pubblicazione: (2025)
• Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning
  di: Son, Guijin, et al.
  Pubblicazione: (2025)