Open access
Aug 2026
Investigating the Impact of Supervision Format on Reasoning Performance in Large Language Models
Treating supervision format as a first-class hyperparameter for multi-task reasoning SFT in large language models—at least in this benchmark-and-model setting—rather than a mere rendering detail is supported.
Nhat Thanh Vu, M. Rashid, Fariza Sabrina
· Electronics · 0 citations