# Unveiling the Key Factors for Distilling Chain-of-Thought Reasoning

arXiv: https://arxiv.org/abs/2502.18001 · HTML: https://mlsanity.com/paper/2502.18001/

## Key facts

- Cited by 40 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 28 of its 38 references that are in the map.
- First posted on arXiv 25 Feb 2025.

## Placed in

- LLM reasoning / [Prompting and chain-of-thought reasoning](https://mlsanity.com/lr/prompting-and-chain-of-thought-reasoning/)
- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 28 of 28)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies](https://mlsanity.com/paper/2101.02235/) (2021)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [Decomposed Prompting: A Modular Approach for Solving Complex Tasks](https://mlsanity.com/paper/2210.02406/) (2022)
- [MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning](https://mlsanity.com/paper/2309.05653/) (2023)
- [Large Language Models Are Reasoning Teachers](https://mlsanity.com/paper/2212.10071/) (2022)
- [Teaching Small Language Models to Reason](https://mlsanity.com/paper/2212.08410/) (2022)
- [Distilling System 2 into System 1](https://mlsanity.com/paper/2407.06023/) (2024)
- [Distilling Reasoning Capabilities into Smaller Language Models](https://mlsanity.com/paper/2212.00193/) (2022)
- [The Impact of Reasoning Step Length on Large Language Models](https://mlsanity.com/paper/2401.04925/) (2024)
- [Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers](https://mlsanity.com/paper/2408.06195/) (2024)
- [Rephrase and Respond: Let Large Language Models Ask Better Questions for Themselves](https://mlsanity.com/paper/2311.04205/) (2023)
- [Faithful Logical Reasoning via Symbolic Chain-of-Thought](https://mlsanity.com/paper/2405.18357/) (2024)
- [A Causal Framework to Quantify the Robustness of Mathematical Reasoning with Language Models](https://mlsanity.com/paper/2210.12023/) (2022)
- [Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation](https://mlsanity.com/paper/2206.06067/) (2022)
- [Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?](https://mlsanity.com/paper/2410.23856/) (2024)
- [What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective](https://mlsanity.com/paper/2410.23743/) (2024)
- [Deciphering the Factors Influencing the Efficacy of Chain-of-Thought: Probability, Memorization, and Noisy Reasoning](https://mlsanity.com/paper/2407.01687/) (2024)
- [Enhancing Zero-shot Chain of Thought Prompting via Uncertainty-Guided Strategy Selection](https://mlsanity.com/paper/2412.00353/) (2024)

## Built on by (most cited first, 30 of 40)

- [Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models](https://mlsanity.com/paper/2503.09567/) (2025)
- [Efficient Reasoning Models: A Survey](https://mlsanity.com/paper/2504.10903/) (2025)
- [Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Inference Time](https://mlsanity.com/paper/2504.12329/) (2025)
- [Purified OPSD: On-Policy Self-Distillation Without Losing How to Think](https://mlsanity.com/paper/2607.02234/) (2026)
- [VeriThinker: Learning to Verify Makes Reasoning Model Efficient](https://mlsanity.com/paper/2505.17941/) (2025)
- [Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation](https://mlsanity.com/paper/2605.16826/) (2026)
- [Latent Chain-of-Thought World Modeling for End-to-End Driving](https://mlsanity.com/paper/2512.10226/) (2025)
- [Reasoning with OmniThought: A Large CoT Dataset with Verbosity and Cognitive Difficulty Annotations](https://mlsanity.com/paper/2505.10937/) (2025)
- [Which Reasoning Trajectories Teach Students to Reason Better? A Simple Metric of Informative Alignment](https://mlsanity.com/paper/2601.14249/) (2026)
- [SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling](https://mlsanity.com/paper/2506.04179/) (2025)
- [Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning](https://mlsanity.com/paper/2510.25992/) (2025)
- [Revisiting Test-Time Scaling: A Survey and a Diversity-Aware Method for Efficient Reasoning](https://mlsanity.com/paper/2506.04611/) (2025)
- [Demystifying Hybrid Thinking: Can LLMs Truly Switch Between Think and No-Think?](https://mlsanity.com/paper/2510.12680/) (2025)
- [The Signal is in the Steps: Local Scoring for Reasoning Data Selection](https://mlsanity.com/paper/2510.03988/) (2025)
- [Merge-of-Thought Distillation](https://mlsanity.com/paper/2509.08814/) (2025)
- [Harnessing Chain-of-Thought Metadata for Task Routing and Adversarial Prompt Detection](https://mlsanity.com/paper/2503.21464/) (2025)
- [Self-Policy Distillation via Capability-Selective Subspace Projection](https://mlsanity.com/paper/2605.22675/) (2026)
- [Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models](https://mlsanity.com/paper/2503.14521/) (2025)
- [The Molecular Structure of Thought: Mapping the Topology of Long Chain-of-Thought Reasoning](https://mlsanity.com/paper/2601.06002/) (2026)
- [Select to Think: Unlocking SLM Potential with Local Sufficiency](https://mlsanity.com/paper/2604.26940/) (2026)
- [Tailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model Compatibility](https://mlsanity.com/paper/2605.29229/) (2026)
- [Function-Aware Fill-in-the-Middle as Mid-Training for Coding Agent Foundation Models](https://mlsanity.com/paper/2607.12463/) (2026)
- [Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning](https://mlsanity.com/paper/2508.10019/) (2025)
- ["The Whole Is Greater Than the Sum of Its Parts": A Compatibility-Aware Multi-Teacher CoT Distillation Framework](https://mlsanity.com/paper/2601.13992/) (2026)
- [Emergent Manifold Separability during Reasoning in Large Language Models](https://mlsanity.com/paper/2602.20338/) (2026)
- [Probing to Refine: Reinforcement Distillation of LLMs via Explanatory Inversion](https://mlsanity.com/paper/2603.19266/) (2026)
- [Fine-Tuning Small Reasoning Models for Quantum Field Theory](https://mlsanity.com/paper/2604.18936/) (2026)
- [When Agents Look the Same: Quantifying Distillation-Induced Similarity in Tool-Use Behaviors](https://mlsanity.com/paper/2604.21255/) (2026)
- [AgentBrew: Lifelong Knowledge Brewing from Strong Teachers to Weak LLM Agents](https://mlsanity.com/paper/2607.16851/) (2026)
- [Systematic Optimization of Open Source Large Language Models for Mathematical Reasoning](https://mlsanity.com/paper/2509.07238/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought (CoT) prompting. However, CoT prompting greatly increases computational demands, which has prompted growing interest in distilling CoT capabilities into Small Language Models (SLMs). This study systematically examines the factors influencing CoT distillation, including the choice of granularity, format and teacher model. Through experiments involving four teacher models and seven student models across seven mathematical and commonsense reasoning datasets, we uncover three key findings: (1) Unlike LLMs, SLMs exhibit a non-monotonic relationship with granularity, with stronger models benefiting from finer-grained reasoning and weaker models performing better with simpler CoT supervision; (2) CoT format significantly impacts LLMs but has minimal effect on SLMs, likely due to their reliance on supervised fine-tuning rather than pretraining preferences; (3) Stronger teacher models do NOT always produce better student models, as diversity and complexity in CoT supervision can outweigh accuracy alone. These findings emphasize the need to tailor CoT strategies to specific student model, offering actionable insights for optimizing CoT distillation in SLMs. The code and datasets are available at https://github.com/EIT-NLP/Distilling-CoT-Reasoning.