notesum.ai

Published at November 6

Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding

cs.AI

cs.CL

cs.LG

stat.ML

I.2.7

Released Date: November 6, 2024

Authors: Haolin Chen¹, Yihao Feng¹, Zuxin Liu¹, Weiran Yao¹, Akshara Prabhakar¹, Shelby Heinecke¹, Ricky Ho¹, Phil Mui¹, Silvio Savarese¹, Caiming Xiong¹, Huan Wang¹

Aff.: ¹Salesforce AI Research

Arxiv: http://arxiv.org/abs/2411.04282v1