@zackankner : Excited to announce our new work: Critique-out-Loud (CLoud) reward models. CLoud reward models first produce a chain of thought critique of the input before predicting a scalar reward, allowing reward models to reason explicitly instead of implicitly! arxiv.org/abs/24508.11791 • TwiCopy

Zack Ankner

@zackankner

+ Follow

Alignment Science @AnthropicAI. Senior @MIT. President of AI@MIT. Prev @DbrxMosaicAI.

ID: 1178454598023024642

linkhttp://zackankner.com calendar_today29-09-2019 23:40:53

353 Tweet

1,1K Takipçi

462 Takip Edilen

Zack Ankner

@zackankner

10 months ago

Excited to announce our new work: Critique-out-Loud (CLoud) reward models. CLoud reward models first produce a chain of thought critique of the input before predicting a scalar reward, allowing reward models to reason explicitly instead of implicitly! arxiv.org/abs/2408.11791

thumb_up_off_alt252

chat_bubble_outline13

repeat59

shareShare