s1: Simple test-time scaling
Muennighoff et al., 2025, s1 (Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing)
Subscriber deck — free during early access
1 cards in “5.2 Test-Time Scaling Methods” · whole deck
5.2 Test-Time Scaling Methods
- Which alternatives to budget forcing failed, and how?Telling the model a token budget failed because it cannot count tokens; with a step budget it hit any target with a similar number of tokens, just spread across more, shorter steps; and rejection sampling to a length limit showed inverse scaling: shorter accepted samples were more often correct, as long ones backtrack a lot.
- Muennighoff et al., 2025, s1 (Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing), §5.2, p. 20282
Source
- Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès and Tatsunori Hashimoto. 2025. s1: Simple test-time scaling. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 20275–20321. License: CC BY 4.0. Flashcards adapted from this work. doi:10.18653/v1/2025.emnlp-main.1025 https://aclanthology.org/2025.emnlp-main.1025/