The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection 事件

The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection arXiv:2605.26872v1 Announce Type: cross Abstract: LLM training increasingly relies on teacher-generated supervision, from synthetic responses to reasoning traces and tool-use demonstrations. Current practice often chooses the highest-performing teacher to generate student training data, implicitly treating teacher test performance as a proxy for teaching quality. We show that this assumption can fail: even wh