Evaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective
Weak-to-strong alignment offers a promising route to scalable supervision, but it can fail when a strong model becomes confidently wrong on examples that lie in the weak model's blind spots. Understanding such failures requires going beyond aggregate accuracy, since weak-to-strong errors depend not only on whether the strong model disagrees with the weak model, but also on how confidence and uncertainty are distributed across examples. In this work, we analyze weak-to-strong alignment through a bias--variance--covariance lens that connects misfit theory to practical post-training pipelines. We derive a misfit-based upper bound on weak-to-strong population risk and study its empirical comp...
| Authors | Hamid Osooli, Kareema Batool, Rick Gentry et al. |
|---|---|
| Primary category | cs.AI |
| Published | 28 April 2026 |
| Last updated at source | 4 August 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.