finding
active
finding:token-filtering-and-reward-shaping-give-strongest-recovery-of-sft-level-formatting-rates-with-minimal-olmes-loss

Token filtering and reward shaping give strongest recovery of SFT-level formatting rates with minimal OLMES loss

Fig. 8.

Source paper

extracted_from
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
(2026) · Leon Bergen · Usha Bhalla · Sidharth Baskaran · Max Loeffler +13

Neighborhood — ranked by edge-count