mlsanityData to 14 Oct 2026

Revisiting the Capacity Gap in Chain-of-Thought Distillation from a Practical Perspective

arXiv 2604.08880 ↗First posted 10 Apr 2026cs.LG cs.AI cs.CLcited by 2

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

also in 1 more
Abstract (arXiv)

Chain-of-thought (CoT) distillation transfers reasoning behaviors from a strong teacher to a smaller student, but prior work reports a capacity gap: distillation may fail when the teacher-student capability mismatch is large. We revisit the capacity gap from a practical perspective by re-examining commonly used experimental settings. Notably, we find that CoT distillation often degrades performance compared to the student's pre-distillation baseline, and that some settings used in prior work, while suitable for establishing the capacity gap as a phenomenon, do not reflect realistic deployment scenarios. Complementing prior work that establishes the capacity gap, we evaluate its practical impact under more realistic settings and find that it does not consistently dominate; stronger teachers tend to be preferable when candidate teachers differ substantially in performance. Our results offer practical guidance for selecting teacher-student pairs in CoT distillation.

Key facts. Cited by 2 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 6 of its 38 references that are in the map. First posted on arXiv 10 Apr 2026.

Builds on

6 of 38 references.

References · 6

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2024Gemma 2: Improving Open Language Models at a Practical Sizecited by 1,998
  5. 2023Orca: Progressive Learning from Complex Explanation Traces of GPT-4cited by 379
  6. 2015Unifying distillation and privileged informationcited by 233

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2025Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning
  2. 2023Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step
  3. 2026Improving Reasoning Capabilities in Small Models through Mixture-of-Layers Distillation with Stepwise Attention on Key Information
  4. 2026Knowledge Distillation Must Account for What It Loses
  5. 2025Merge-of-Thought Distillation
  6. 2026When Compression Helps and When It Hurts: Condition-Aware Analysis of Chain-of-Thought Distillation
  7. 2026Solving Without Stopping: On-Policy Distillation at Small Scale
  8. 2024Investigating Mysteries of CoT-Augmented Distillation