Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations

By Peiyi Wang, Lei Li, Zhihong Shao, Runxin Xu, Damai Dai, Yifei Li, Deli Chen, Y.Wu, Zhifang Sui. 2023

1,036 citations recorded by the source corpus.

In this paper, we present an innovative process-oriented math process reward model called \textbf{Math-Shepherd}, which assigns a reward score to each step of math problem solutions. The training of Math-Shepherd is achieved using automatically constructed process-wise supervision data, breaking the bottleneck of heavy reliance on manual annotation in existing work. We explore the effectiveness of Math-Shepherd in two scenarios: 1) \textit{Verification}: Math-Shepherd is utilized for reranking multiple outputs generated by Large Language Models (LLMs); 2) \textit{Reinforcement Learning}: Math-Shepherd is employed to reinforce LLMs with step-by-step Proximal Policy Optimization (PPO). With Math-Shepherd, a series of open-source LLMs demonstrates exceptional performance. For instance, the step-by-step PPO with Math-Shepherd significantly improves the accuracy of Mistral-7B (77.9\%$\to$84.1\% on GSM8K and 28.6\%$\to$33.0\% on MATH). The accuracy can be further enhanced to 89.1\% and 43.5\% on GSM8K and MATH with the verification of Math-Shepherd, respectively. We believe that automatic process supervision holds significant potential for the future evolution of LLMs.

Subfields: Artificial Intelligence, 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. Wenhai Wang
  2. Lewei Lu
  3. Peiyi Wang
  4. Zhihong Shao
  5. Weijie Su
  6. Mingchuan Zhang
  7. Yinan He
  8. Jun-Mei Song

In Large Language Models

  1. Peiyi Wang
  2. Zhihong Shao
  3. Yinan He
  4. Conghui He
  5. Daya Guo
  6. Xizhou Zhu
  7. Yu Wu

In Prompting & Reasoning

  1. Zhihong Shao
  2. Daya Guo

Citations in the corpus