Scalable Oversight: Debate / Weak-to-Strong Generalization

Editorial record

Plain-language summary

The weak-to-strong experiments used a small model's imperfect labels to fine-tune a much larger pretrained model and found the larger model generalized beyond its teacher's errors, an analogy for humans supervising superhuman systems. Related debate proposals have two models argue opposing positions so a limited judge can adjudicate claims it could not verify directly. Together these define the scalable-oversight problem and give early empirical evidence that supervision signal can transfer even when the supervisor is less capable than the system being trained.