🧑‍🔬 Han Shi

🏛️ Affiliations

🏢Microsoft Research AsiaBeijing · China2006–2026 · 60 paperscurrent🏢MicrosoftRedmond · United States2013–2026 · 19 paperscurrent🎓Hong Kong University of Science and TechnologyHong Kong · China2019–2025 · 8 papers🎓Tsinghua UniversityBeijing · China2011–2018 · 6 papers🎓Hangzhou Normal UniversityHangzhou · China2024–2025 · 2 papers🎓Center for Excellence in Molecular Plant SciencesShanghai · China2018–2021 · 2 papers🏛️Chinese Academy of SciencesBeijing · China2018–2021 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 8 more institutions on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models (2023 · 565 citations)
   Open-source LLMs such as LLaMA-2 lag well behind closed models on multi-step maths word problems. Fine-tuning helps, but it depends on having enough varied training questions. MetaMath addresses this by growing the GSM8K and MATH training sets from the question side as well as the answer side, producing a dataset…
2. LEGO-Prover: Neural Theorem Proving with Growing Libraries (2023 · 79 citations)
   Formal theorem proving is still hard for large language models. Existing LLM-based provers often fail on competition problems at middle-school level. These "plain" provers write each proof as one long monolithic block and treat the available theorem library as fixed. So a lemma proved for one problem cannot help with…

All works

4 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. MetaMath: Bootstrap Your Own Mathematical Questions for Large Language ModelsarXiv:2309.12284Longhui Yu, Weisen Jiang, Han Shi, et al.2023 · 565 citations
2. LEGO-Prover: Neural Theorem Proving with Growing LibrariesarXiv:2310.00656Haiming Wang, Huajian Xin, Chuanyang Zheng, et al.2023 · 79 citations
3. HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetZhoujun Cheng et al.2022 · 61 citations
4. FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining ↗Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetZhoujun Cheng et al.2022 · 36 citations

🤝 Co-authors here

12 of 14 co-authors with a page, the most papers together first.

• Zhenguo Li ×2
• Zhengying Liu ×2
• Chuanyang Zheng
• Enze Xie
• Haiming Wang
• Huajian Xin
• James Tin-Yau Kwok
• Jian Yin
• Jincheng Yu
• Jing Xiong
• Lin Li
• Qingxing Cao

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) ×2
• ACM International Conference on Web Search and Data Mining (WSDM)

🔗 Cited by

Papers of our library cite their works 717 times (of the 149,439 papers whose bibliographies we read); 211 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/han-shi/