#machine learning
Jun 2026
CODEBLOCK: Learning to Supervise Code at the Right Granularity
Experiments show that partial supervision over only about 6.9% of response tokens consistently outperforms full-token SFT across all five model settings, suggesting that effective code SFT depends not only on identifying high-value supervision, but also on allocating it at the appropriate structural granularity.
Zhi-Jie Deng, Ling Li, Jinlong Pang et al.
· arXiv.org · 1 citation