SOURCE-LINKED INTELLIGENCE

Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Supervised fine-tuning (SFT) applies a uniform cross-entropy loss to all target tokens, even though different tokens provide unequal learning signals for mathematical reasoning. This uniform treatment can over-sharpen already mastered tokens while amplifying learning pressure on uncertain, low-confidence tokens, leading to suboptimal training dynamics. We propose Trimmed Logit-Gap SFT (TrimSFT), a simple token-level reweighting method that scales the SFT loss according to the logit gap between the gold token and its strongest competitor. TrimSFT trims supervision away from both extremes: token

Read original source ↗ Open in workspace

recordType

paper

region

Global