#reward-modeling on Hacker News

2 stories tagged reward-modeling, newest first.

Screenshot of di-zhang-llm.github.io: What Is RLCD? The Secret Behind Jev

What Is RLCD? The Secret Behind Jev (di-zhang-llm.github.io)

51 points by tnspacetime 1 month ago | 6 comments

Blog post by Fudan PhD candidate Di Zhang explaining RLCD, a calibrated reward modeling approach building on PPRM and Plackett-Luce, and its role in Jev.

reward-modeling rlcd jev plackett-luce

RLHF Book (rlhfbook.com)

439 points by jxmorris12 1 year ago | 34 comments

Online book by Nathan Lambert giving a short introduction to reinforcement learning from human feedback and post-training for language models.

rlhf reinforcement-learning language-models post-training

#reward-modeling on Hacker News

What Is RLCD? The Secret Behind Jev(di-zhang-llm.github.io)

RLHF Book(rlhfbook.com)

What Is RLCD? The Secret Behind Jev (di-zhang-llm.github.io)

RLHF Book (rlhfbook.com)