--- aliases: en: - W2SG - weak to strong generalization concept_id: weak_to_strong_generalization preferred: en: weak-to-strong generalization relations: relations: broader: - generalization prerequisite: - generalization status: active --- # weak-to-strong generalization A weak-supervision research setting, and the generalization phenomenon it tests, in which a stronger learner is trained using imperfect labels or demonstrations from a weaker supervisor and is evaluated on whether it can outperform that supervisor, ideally approaching capabilities already available to the stronger learner; it is studied as an empirical analogue of humans supervising superhuman AI systems. ## broader - [generalization](../terminology/generalization.txt) ## prerequisite - [generalization](../terminology/generalization.txt) ## Documents: about - [弱い監視者でも、強いモデルの潜在能力の一部を引き出せる場合がある](../documents/openai.weak-to-strong-supervision-can-recover-some-latent-capability.txt) - [weak-to-strong で高い性能が出ても、弱い supervisor が知らない領域で alignment が保たれるとは限らない](../documents/yang_et_al.weak-to-strong-success-can-hide-selective-misalignment.txt) [Corpus index](../index.txt)