REVIEW 2 cited by
Transcendence: Generative Models Can Outperform The Experts That Train Them
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Generative models are trained with the simple objective of imitating the conditional probability distribution induced by the data they are trained on. Therefore, when trained on data generated by humans, we may not expect the artificial model to outperform the humans on their original objectives. In this work, we study the phenomenon of transcendence: when a generative model achieves capabilities that surpass the abilities of the experts generating its data. We demonstrate transcendence by training an autoregressive transformer to play chess from game transcripts, and show that the trained model can sometimes achieve better performance than all players in the dataset. We theoretically prove that transcendence can be enabled by low-temperature sampling, and rigorously assess this claim experimentally. Finally, we discuss other sources of transcendence, laying the groundwork for future investigation of this phenomenon in a broader setting.
Forward citations
Cited by 2 Pith papers
-
Relating Misfit to Gain in Weak-to-Strong Generalization Beyond the Squared Loss
For convex and approximately convex model classes, the loss gain in weak-to-strong learning is at least the KL misfit between strong and weak models, plus an error term that vanishes as k grows.
-
Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges
Iterative self-training on a model's own correct outputs, with simple length and voting filters, lets transformers generalize to far longer arithmetic and path-finding problems than they saw in training.
Discussion (0). Continue with ORCID to comment.