Lets_Verify_Step_by_Step报告原文分析.pdf

Let’s Verify Step by Step Hunter Lightman∗ Vineet Kosaraju∗ Yura Burda∗ Harri Edwards Bowen Baker Teddy Lee Jan Leike John Schulman Ilya Sutskever Karl Cobbe∗ OpenAI Abstract In recent years, large language models have greatly improved in their ability to perform complex multi-step reasoning. However, even state- of-the-art models still regularly produce logical mistakes. To train more reliable models, we can turn either to outcome supervision, which provides feedback for a final result, or process supervision, which provides feedback for each intermediate reasoning step. Given the importance of training reliable models, and given the high cost of human feedback, it is impor- tant to carefully compare the both methods. Recent work has already begun this comparison, but many questions still remain. We conduct our own investigation, finding that process supervision significantly outper- forms outcome supervision for training models to solve problems from the challenging MATH dataset. Our process-supervised model solves 78% of problems from a representative subset of the MATH test set. Additionally, we show that active learning significantly improves the efficacy of process supervision. To support related research, we also release PRM800K, the complete dataset of 800,000 step-level human feedback labels used to train our best reward model. 1 Introduction Large language models are capable of solving tasks that require complex multi- step reasoning by generating solutions in a step-by-step chain-of-thought format (Nye et al.,