作者位次 #7/10ACL 2026Findings· Findings of ACL
E nsem W 2 S : Enhancing Weak-to-Strong Generalization with Large Language Model Ensembles
Aakriti Agrawal · Mucong Ding · Chenghao Deng · Zora Che · Arjun Rajaram · Anirudh Satheesh · Bang An · C. Bayan Bruss · John Langford · Furong Huang
摘要
With Large Language Models (LLMs) rapidly approaching and potentially surpassing human-level performance, it has become imperative to develop approaches capable of effectively supervising and enhancing these powerful models using smaller, human-level models exposed to only human-level data. We ad...