Work

Fast and Effective On-Policy Distillation from Reasoning Prefixes

Year: 2026
Type: conference-paper
Abstract: Dongxu Zhang, Zhichao Yang, Sepehr Janghorbani, Jun Han, Andrew Ressler II, Qian Qian, Gregory D Lyng, Sanjit Singh Batra, Robert E. Tillman. Findings of the Association for Computational Linguistics: ACL 2026. 2026.
Language: English
Open Access status: hybrid
OpenAlex ID: W7166866843
FWCI:
Cites:
Cited by:
Related to: 10