Let’s Verify Step by Step
Lightman et al., 2024, Let’s Verify Step by Step (The Twelfth International Conference on Learning Representations (ICLR 2024))
Subscriber deck — free during early access
1 cards in “7 Related Work” · whole deck
7 Related Work
- How do Lightman et al. reconcile their results with Uesato et al.’s finding of no difference?Data scale: their scaling curves show a little process supervision matching a lot of outcome supervision, as Uesato et al. saw, but process supervision pulling ahead as more is collected.
- Lightman et al., 2024, Let’s Verify Step by Step (The Twelfth International Conference on Learning Representations (ICLR 2024)), §7
Source
- Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever and Karl Cobbe. 2024. Let’s Verify Step by Step. In The Twelfth International Conference on Learning Representations (ICLR 2024). https://arxiv.org/abs/2305.20050