Zenaique
Topics
Practice
Browse
Reference
Challenges
Pricing
Search…
⌘K
Topics
/
Fine-Tuning
/
Reference Policy
Reference Policy
Subtopic
1 questions
Questions tagged with Reference Policy — part of Fine-Tuning.
Format
Difficulty
Role
Experience
Companies
Sort
Newest
Quality
Difficulty ↑
Difficulty ↓
Questions
DPO: what's the closed-form trick that lets it skip the reward model?
Short Answer
Hard
·
Qual 4.0