Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can reduce response length while degrading performance. We trace this degradation to the suppression of epistemic verbalization - the model's expression of uncertainty during reasoning. Through controlled experiments varying conditioning context richness and task coverage, we show that conditioning the teacher on rich information suppresses uncertainty expression, enabling rapid in-domain optimization with limited task coverage but harming OOD performance, where unseen problems benefit from expressing uncertainty and adjusting accordingly. Across Qwen3-1.7B/8B, DeepSeek-Distill-Qwen-7B, and Olmo3-7B-Instruct, we observe performance drops of up to 40%. Our findings highlight that exposing appropriate levels of uncertainty is crucial for robust reasoning and underscore the importance of optimizing reasoning behavior beyond merely reinforcing correct answer traces.
Code (0)
등록된 구현이 없습니다.
Tasks
Mathematical ReasoningSimilar Papers 제목 키워드 기반
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference trace or hint, the same policy provides…
Mathematical ReasoningOPSD Compresses What RLVR Teaches: A Post-RL Compaction Stage for Reasoning Models
On-Policy Self-Distillation (OPSD) has recently emerged as an alternative to Reinforcement Learning with Verifiable Rewards (RLVR), promising higher accuracy and shorter responses through token-level credit assignment fr…
Reinforcement LearningMathematical ReasoningTraining with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
Inference-time harnesses substantially improve large language models on complex reasoning tasks. However, the intrinsic capabilities of the underlying model remain unchanged by the addition of these external workflows. T…
Mathematical ReasoningText ClassificationSelf-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
Knowledge distillation improves large language model (LLM) reasoning by compressing the knowledge of a teacher LLM to train smaller LLMs. On-policy distillation advances this approach by having the student sample its own…
Knowledge DistillationMathematical ReasoningReinforcement LearningRethinking On-Policy Self-Distillation for Thinking Models
Self-distillation is a promising recipe for self-improvement in language models. In this setting, a model can serve as its own teacher when given privileged information, such as a solution to a math problem. This seems e…