Improving Mathematical Reasoning Capabilities in Large Language Models via Reasoning Process Error Classification

arXiv:2609.15145 · cs.CL · Submitted 2026-09-14 · Read on arXiv

cs.CL

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 10 pages

Code: https://github.com/deepseek-ai/DeepSeekMath

License: http://creativecommons.org/licenses/by/4.0/

The gist: The reasoning ability of large language models (LLMs) is a critical factor for practical LLM-based applications.

Terminology

Abstract

The reasoning ability of large language models (LLMs) is a critical factor for practical LLM-based applications. To investigate the current reasoning capability of LLMs, we clarify the types of errors that arise in LLMs' reasoning processes on mathematical datasets. We focus on problems where LLMs produce an incorrect answer. We define errors in the reasoning process as reasoning errors and manually analyze the features of reasoning errors. We defined and classified 21 error classes and identified the frequently occurring classes among them. Beyond qualitative evaluation, we leverage the evaluation results to improve the reasoning capability. We designed a prompt that explicitly focuses on eight error classes. The experiments demonstrate that this prompt effectively improves reasoning performance. Furthermore, the results suggest that the frequent reasoning errors identified in this paper are common across LLMs of comparable scale.

Sources

Related papers