# Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs? arXiv: https://arxiv.org/abs/2603.24472 ยท HTML: https://mlsanity.com/paper/2603.24472/ ## Key facts - Cited by 103 papers in the map (data through 14 Oct 2026). - Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. - Builds on 20 of its 29 references that are in the map. - First posted on arXiv 25 Mar 2026. ## Placed in - LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/) - Knowledge distillation / [On-policy and self-distillation for LLMs](https://mlsanity.com/distill/on-policy-and-self-distillation-for-llms/) ## Builds on (most cited first, 20 of 20) - [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025) - [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025) - [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024) - [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024) - [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025) - [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026) - [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023) - [Reinforcement Learning via Self-Distillation](https://mlsanity.com/paper/2601.20802/) (2026) - [Self-Distillation Enables Continual Learning](https://mlsanity.com/paper/2601.19897/) (2026) - [On-Policy Context Distillation for Language Models](https://mlsanity.com/paper/2602.12275/) (2026) - [Learning by Distilling Context](https://mlsanity.com/paper/2209.15189/) (2022) - [Privileged Information Distillation for Language Models](https://mlsanity.com/paper/2602.04942/) (2026) - [Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning](https://mlsanity.com/paper/2508.09726/) (2025) - [Expanding the Capabilities of Reinforcement Learning via Text Feedback](https://mlsanity.com/paper/2602.02482/) (2026) - [Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization](https://mlsanity.com/paper/2602.23008/) (2026) - [Understanding Reasoning in LLMs through Strategic Information Allocation under Uncertainty](https://mlsanity.com/paper/2603.15500/) (2026) - [Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning](https://mlsanity.com/paper/2602.03249/) (2026) - [ConPress: Learning Efficient Reasoning from Multi-Question Contextual Pressure](https://mlsanity.com/paper/2602.01472/) (2026) - [Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning](https://mlsanity.com/paper/2602.22642/) (2026) - [In-Token Rationality Optimization: Towards Accurate and Concise LLM Reasoning via Self-Feedback](https://mlsanity.com/paper/2511.09865/) (2025) ## Built on by (most cited first, 30 of 103) - [Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe](https://mlsanity.com/paper/2604.13016/) (2026) - [A Survey of On-Policy Distillation for Large Language Models](https://mlsanity.com/paper/2604.00626/) (2026) - [Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing](https://mlsanity.com/paper/2604.02288/) (2026) - [The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes](https://mlsanity.com/paper/2605.11182/) (2026) - [Rethinking On-Policy Self-Distillation for Thinking Models](https://mlsanity.com/paper/2607.05184/) (2026) - [Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation](https://mlsanity.com/paper/2606.02684/) (2026) - [Purified OPSD: On-Policy Self-Distillation Without Losing How to Think](https://mlsanity.com/paper/2607.02234/) (2026) - [Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models](https://mlsanity.com/paper/2604.08527/) (2026) - [Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning](https://mlsanity.com/paper/2605.07804/) (2026) - [KL for a KL: On-Policy Distillation with Control Variate Baseline](https://mlsanity.com/paper/2605.07865/) (2026) - [Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why](https://mlsanity.com/paper/2605.10889/) (2026) - [Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning](https://mlsanity.com/paper/2605.13255/) (2026) - [Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation](https://mlsanity.com/paper/2608.04794/) (2026) - [STEPS: Selective On-Policy Self-Distillation for Reasoning](https://mlsanity.com/paper/2605.10194/) (2026) - [OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning](https://mlsanity.com/paper/2605.12400/) (2026) - [Trajectory-Refined Distillation](https://mlsanity.com/paper/2606.08432/) (2026) - [Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR](https://mlsanity.com/paper/2605.10781/) (2026) - [On-Policy Delta Distillation](https://mlsanity.com/paper/2607.15161/) (2026) - [Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information](https://mlsanity.com/paper/2605.11609/) (2026) - [Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization](https://mlsanity.com/paper/2605.05040/) (2026) - [Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation](https://mlsanity.com/paper/2605.15239/) (2026) - [OPRD: On-Policy Representation Distillation](https://mlsanity.com/paper/2606.06021/) (2026) - [Crosslingual On-Policy Self-Distillation for Multilingual Reasoning](https://mlsanity.com/paper/2605.09548/) (2026) - [Multi-Rollout On-Policy Distillation via Peer Successes and Failures](https://mlsanity.com/paper/2605.12652/) (2026) - [Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning](https://mlsanity.com/paper/2605.22263/) (2026) - [Reinforcement Learning from Rich Feedback with Distributional DAgger](https://mlsanity.com/paper/2606.05152/) (2026) - [The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation](https://mlsanity.com/paper/2604.16830/) (2026) - [Breaking the Tokenizer Barrier: On-Policy Distillation across Model Families](https://mlsanity.com/paper/2606.09456/) (2026) - [Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning](https://mlsanity.com/paper/2608.01589/) (2026) - [Rethinking Privileged Information in On-Policy Self-Distillation](https://mlsanity.com/paper/2608.18271/) (2026) ## Abstract (arXiv) 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.