learn.ifs.name

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

Shao et al., 2024, DeepSeekMath (arXiv preprint arXiv:2402.03300)

Subscriber deck — free during early access

1 cards in “6 Conclusion, Limitation, and Future Work” · whole deck

6 Conclusion, Limitation, and Future Work

  1. What weaknesses of DeepSeekMath do its authors note?
    Geometry and theorem proving lagged behind closed models (e.g. problems on triangles and ellipses), possibly from data-selection bias; and at 7B it gained little from few-shot examples, unlike GPT-4.
    • Shao et al., 2024, DeepSeekMath (arXiv preprint arXiv:2402.03300), §6

Source

  • Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, Y. K. Li, Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. In arXiv preprint arXiv:2402.03300. https://arxiv.org/abs/2402.03300