activity
20242026
most citedCritic-CoT: Boosting the reasoning abilities of large language model via Chain-of-thoughts Critic

1 citations · 2 across the 10 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2025

Scalable Oversight for Superhuman AI via Recursive Self-Critiquing

Xueru Wen, Jie Lou, Xinyu Lu +5

As AI capabilities increasingly surpass human proficiency in complex tasks, current alignment techniques, including SFT and RLHF, face fundamental challenges in ensuring reliable o…