On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation
Read the original on arXiv AI →The paper investigates how on-policy self‑distillation can alter a model’s behavior by conditioning on privileged information. It contrasts attractive self‑distillation, which pulls a model toward a privileged teacher, with repulsive self‑distillation, which pushes it away, showing that attraction reduces exploratory reasoning while repulsion lengthens responses and can destabilize the model. The authors propose a contrastive self‑distillation objective that combines attraction to a correct‑solution teacher with repulsion from an incorrect‑solution teacher, finding that this approach improves reasoning performance across various model types while keeping response lengths stable.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.