The Mechanism of Weak-to-Strong Generalization: Feature Elicitation from Latent Knowledge
arXiv:2605.12908v1 Announce Type: new
Abstract: Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an approach to aligning superhuman AI systems. Existing the…