DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

By Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Jun-Mei Song, Mingchuan Zhang, Y. K. Li, Yu Wu, Daya Guo. 2024

7,648 citations recorded by the source corpus.

Mathematical reasoning poses a significant challenge for language models due to its complex and structured nature. In this paper, we introduce DeepSeekMath 7B, which continues pre-training DeepSeek-Coder-Base-v1.5 7B with 120B math-related tokens sourced from Common Crawl, together with natural language and code data. DeepSeekMath 7B has achieved an impressive score of 51.7% on the competition-level MATH benchmark without relying on external toolkits and voting techniques, approaching the performance level of Gemini-Ultra and GPT-4. Self-consistency over 64 samples from DeepSeekMath 7B achieves 60.9% on MATH. The mathematical reasoning capability of DeepSeekMath is attributed to two key factors: First, we harness the significant potential of publicly available web data through a meticulously engineered data selection pipeline. Second, we introduce Group Relative Policy Optimization (GRPO), a variant of Proximal Policy Optimization (PPO), that enhances mathematical reasoning abilities while concurrently optimizing the memory usage of PPO.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Large Language Models, Prompting & Reasoning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Zhiyuan Liu
  2. Maosong Sun
  3. Mohit Bansal
  4. Xu Han
  5. Jianfeng Gao
  6. Ning Ding
  7. Graham Neubig
  8. Percy Liang

In Computational Theory and Mathematics

  1. Damai Dai
  2. Vitaliy Chiley
  3. Mohit Bansal
  4. Noah D. Goodman
  5. Yuan Yao
  6. Jingren Zhou
  7. Maosong Sun
  8. John P. Cunningham

In Large Language Models

  1. Zhiyuan Liu
  2. Maosong Sun
  3. Mohit Bansal
  4. Swarnadeep Saha
  5. J. Chen
  6. Damai Dai
  7. Noah D. Goodman
  8. Zhihong Shao

In Prompting & Reasoning

  1. Zhiyuan Liu
  2. Mohit Bansal
  3. Ning Ding
  4. Maosong Sun
  5. Swarnadeep Saha
  6. J. Chen
  7. Damai Dai
  8. Noah D. Goodman

Citations in the corpus