English

Distilling Mathematical Reasoning Capabilities into Small Language Models

Computation and Language 2024-08-02 v5 Artificial Intelligence

Abstract

This work addresses the challenge of democratizing advanced Large Language Models (LLMs) by compressing their mathematical reasoning capabilities into sub-billion parameter Small Language Models (SLMs) without compromising performance. We introduce Equation-of-Thought Distillation (EoTD), a novel technique that encapsulates the reasoning process into equation-based representations to construct an EoTD dataset for fine-tuning SLMs. Additionally, we propose the Ensemble Thoughts Distillation (ETD) framework to enhance the reasoning performance of SLMs. This involves creating a reasoning dataset with multiple thought processes, including Chain-of-Thought (CoT), Program-of-Thought (PoT), and Equation-of-Thought (EoT), and using it for fine-tuning. Our experimental performance demonstrates that EoTD significantly boosts the reasoning abilities of SLMs, while ETD enables these models to achieve state-of-the-art reasoning performance.

Keywords

Cite

@article{arxiv.2401.11864,
  title  = {Distilling Mathematical Reasoning Capabilities into Small Language Models},
  author = {Xunyu Zhu and Jian Li and Yong Liu and Can Ma and Weiping Wang},
  journal= {arXiv preprint arXiv:2401.11864},
  year   = {2024}
}

Comments

Accepted for publication in Neural Networks

R2 v1 2026-06-28T14:23:23.794Z