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 “4.2 Active Learning” · whole deck
4.2 Active Learning
- How much did active learning help process supervision?Choosing mostly convincing wrong-answer samples for labelling was about 2.6× more data-efficient than labelling uniformly sampled solutions. Iteratively retraining the selector during collection was unstable and didn’t help.
- Lightman et al., 2024, Let’s Verify Step by Step (The Twelfth International Conference on Learning Representations (ICLR 2024)), §4.2
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