Negative Self-Distillation: Learning to Reason by Avoiding Flaws
Ranking
Overall
86
Content
95
Popularity
66
Observed public metrics from 1 member.
Merged summary
TL;DR - Negative Self-Distillation (NSD) improves LLM reasoning by teaching models to diverge from self-generated flawed reasoning rather than imitate privileged, artificially confident solutions. This preserves exploratory and self-corrective behavior that conventional on-policy self-distillation may suppress.
- NSD requires neither ground-truth answers nor external supervision; the model generates a question-specific negative persona, such as a “careless reasoner.”
- A dynamic gating mechanism isolates reasoning-critical tokens so training targets behavioral flaws without degrading foundational language abilities.
- The approach addresses the confounding of flawed reasoning with ordinary linguistic tokens that makes naive unlearning objectives risky.
- NSD reportedly outperforms on-policy self-distillation and other label-free, self-bootstrapping reinforcement-learning baselines.
Sources (1)
Negative Self-Distillation: Learning to Reason by Avoiding Flaws
Public signals
Hugging Face upvotes 35
TL;DR - Negative Self-Distillation (NSD) improves LLM reasoning by teaching models to diverge from self-generated flawed reasoning rather than imitate privileged, artificially confident solutions. This preserves exploratory and self-corrective behavior that conventional on-policy self-distillation may suppress.
- NSD requires neither ground-truth answers nor external supervision; the model generates a question-specific negative persona, such as a “careless reasoner.”
- A dynamic gating mechanism isolates reasoning-critical tokens so training targets behavioral flaws without degrading foundational language abilities.
- The approach addresses the confounding of flawed reasoning with ordinary linguistic tokens that makes naive unlearning objectives risky.
- NSD reportedly outperforms on-policy self-distillation and other label-free, self-bootstrapping reinforcement-learning baselines.