Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision

14 January 2025

Papers citing "Iterative Label Refinement Matters More than Preference Optimization under Weak Supervision"

2 / 2 papers shown

Title
On the Emergence of Weak-to-Strong Generalization: A Bias-Variance Perspective Gengze Xu Wei Yao Ziqiao Wang Yong Liu 46 0 0 30 May 2025
ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning Bo Liu Yunxiang Li Yangqiu Song Hanjing Wang Linyi Yang ... Jun Wang Jun Wang Weinan Zhang Shuyue Hu Ying Wen LLMAG KELM LRM AI4CE 134 11 0 12 Mar 2025