# Skip-Thinking: Chunk-wise Chain-of-Thought Distillation Enable Smaller Language Models to Reason Better and Faster

Authors: Xiaoshu Chen, Sihang Zhou, Ke Liang, Xiaoyu Sun, Xinwang Liu.

Splits teacher rationales into chunks, then trains a student to skip chunks whose removal preserves the answer. The model retains key written steps while internalizing transitional or summary chunks.

First public: 2025-05-24.
ArXiv initial submission: 2025-05-24.

[Original paper](https://arxiv.org/abs/2505.18642) · [PDF](https://arxiv.org/pdf/2505.18642) · [HTML](https://arxiv.org/html/2505.18642v1) · [Reading-list entry](https://latent-implicit-thinking.github.io/papers/2505.18642/)
[Preprint BibTeX](https://latent-implicit-thinking.github.io/papers/2505.18642/citation.bib) · [Preprint CSL-JSON](https://latent-implicit-thinking.github.io/papers/2505.18642/citation.csl.json) · [JSON record](https://latent-implicit-thinking.github.io/papers/2505.18642/record.json)

## Approaches

- [Internalized reasoning](https://latent-implicit-thinking.github.io/topics/internalized-reasoning/): Learn from worked solutions so that some or all of the reasoning can later happen without writing those steps. Training may use a separate teacher model or progressively remove written steps from the model being trained.

Reading-list version 0.12.0; literature checked through 2026-11-02.