Weak-to-Strong Generalization under Distribution Shifts

Myeongho Jeon, Jan Sobotka, Suhwan Choi, Maria Brbic

Keywords: Weak-to-strong generalization, Distribution shift

TL;DR: This paper introduces a novel scenario, weak-to-strong generalization under distribution shifts, and proposes Robust AdaptiVe wEightiNg (RAVEN) to tackle this challenge.

Abstract:

As future superhuman models become increasingly complex, accurately supervising their behavior may exceed human capabilities.
Recent works have demonstrated that in such scenarios, weak models can effectively supervise strong models, a phenomenon known as weak-to-strong generalization. However, we find that naive weak-to-strong generalization fails under distribution shifts, often leading to worse performance of the strong model than its weak supervisors. To address this, we propose RAVEN, a robust weak-to-strong generalization framework that dynamically learns the optimal combinations of weak models in addition to parameters of the strong model. We demonstrate the effectiveness of RAVEN on image classification, text classification, and preference alignment tasks. RAVEN outperforms alternative baselines by over 30% on out-of-distribution tasks while matching or surpassing existing methods on in-distribution tasks. Moreover, our results show that RAVEN assigns higher weights to more accurate weak models, demonstrating its ability to automatically identify trustworthy supervision.

Primary Area: Deep learning (e.g., architectures, generative models, optimization for deep networks, foundation models, LLMs)

Submission Number: 17027