Haoxiong Liu
Haoxiong Liu has 3 papers in our library, in 2024–2025, most of them on Reasoning; often with Andrew Chi-Chih Yao, Jianyuan Zhong, Jing Xiong.
OpenAlex · h-index 0 · 2 works · 0 citations OpenAlex, 2026-10-14
📄 3 works in our library · 🔗 Cited 52 times in our library · ⭐ Paper Stars ranking: #9484
Fields, topics and concepts
📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 3 worksArts and Humanities · 2 worksArtificial Intelligence · 3 worksComputational Theory and Mathematics · 3 worksLanguage and Linguistics · 2 worksMathematics · 1 workApplied Mathematics · 1 work
🧭 Topics 1Research subjects and languages the work is about.Reasoning · 3 works
Works by year
2020s
Papers
- Augmenting Math Word Problems via Iterative Question Composing (2024 · 44 citations)
Open-source LLMs still do poorly on competition-level mathematics such as the MATH benchmark when they cannot call external tools. - Mathesis: Towards Formal Theorem Proving from Natural Languages (2025 · 9 citations)
Current LLM theorem provers for Lean 4 assume their input is already a formal statement written by an expert. Real problems, however, are stated in natural language. Mathesis targets the full chain from informal problem to verified proof. Its pipeline has three stages: - ProofAug: Efficient Neural Theorem Proving via Fine-grained Proof Structure Analysis (2025 · 4 citations)
Neural theorem provers that combine LLMs with automation tools (built-in tactics, Sledgehammer-style ATPs) usually call those tools only where the model explicitly asks, or at a single level of detail.
Co-authors here
- Andrew Chi-Chih Yao ×2
- Jianyuan Zhong
- Jing Xiong
- Roozbeh Yousefzadeh
- Yifan Luo
- Yifan Zhang
- Zhenguo Li
- Zijin Feng
Venues
- Proceedings of the AAAI Conference on Artificial Intelligence: Proceedings of the AAAI Conference on Artificial Intelligence 2024
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/haoxiong-liu/