ML Wiki

Tag: dpo

5 items with this tag.

  • May 05, 2026

    Self-Rewarding Language Models

    • source
    • alignment
    • rlhf
    • dpo
    • reward-model
    • sft
    • ai-feedback
  • Apr 29, 2026

    ORPO: Monolithic Preference Optimization without Reference Model

    • source
    • alignment
    • dpo
    • rlhf
    • sft
    • training
  • Apr 28, 2026

    What's the right alignment stack post-RLHF?

    • thread
    • alignment
    • rlhf
    • dpo
  • Apr 22, 2026

    KTO: Model Alignment as Prospect Theoretic Optimization

    • source
    • alignment
    • rlhf
    • dpo
    • reward-model
    • training
  • Apr 17, 2026

    KTO: Model Alignment as Prospect Theoretic Optimization

    • source
    • alignment
    • dpo
    • rlhf
    • preference-learning