Your Weak LLM is Secretly a Strong Teacher for Alignment

13 September 2024

Papers citing "Your Weak LLM is Secretly a Strong Teacher for Alignment"

4 / 4 papers shown

Title
Redefining Superalignment: From Weak-to-Strong Alignment to Human-AI Co-Alignment to Sustainable Symbiotic Society Feifei Zhao Y. Wang Enmeng Lu Dongcheng Zhao Bing Han ... Chao Liu Yaodong Yang Yi Zeng Boyuan Chen Jinyu Fan 52 52 0 24 Apr 2025
Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors Fan Nie Lan Feng Haotian Ye Weixin Liang Pan Lu Huaxiu Yao Alexandre Alahi James Zou 47 0 0 07 Apr 2025
Weak-to-Strong Generalization Even in Random Feature Networks, Provably Marko Medvedev Kaifeng Lyu Dingli Yu Sanjeev Arora Zhiyuan Li Nathan Srebro 76 0 0 04 Mar 2025
Provable Weak-to-Strong Generalization via Benign Overfitting David X. Wu A. Sahai 33 6 0 06 Oct 2024