DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
arXiv:2402.03300
Abstract
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.
Cited by in corpus (8)
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Reasoning Beyond Limits: Advances and Open Problems for LLMs
- Transforming Agency. On the mode of existence of Large Language Models
- A recent evaluation on the performance of LLMs on radiation oncology physics using questions of randomly shuffled options
- Large Language Models for Combinatorial Optimization: A Systematic Review
- Leveraging Label Semantics and Meta-Label Refinement for Multi-Label Question Classification
- Large Language Models -- the Future of Fundamental Physics?
- End-to-End Bangla AI for Solving Math Olympiad Problem Benchmark: Leveraging Large Language Model Using Integrated Approach