PdfDing
Add
M
M
mail.dark4scope@gmail.com
User ID: 1
Settings
Admin
Sign out
Back to App
Details
Highlights
Comments
PdfDing
v1.9.0
04 · DPO — Your Language Model is Secretly a Reward Model
Edit
Share
Download
Star
Archive
Collection
Default
Edit
Tags
#
alignment
#
dpo
#
must-read
#
post-training
#
stanford
Edit
Description
从 PPO 的 KL 正则最优解反解 reward。读 §4 + Appendix A.1,必须自己纸上推一遍
Edit
Notes
no notes available
Edit
Views
6
Progress
4% - Page 1 of 27
Date added
Aug. 14, 2026, 9:33 a.m.
Confirm
Cancel
Delete