🧑‍🔬 Jingxuan He

🏛️ Affiliations

🎓University of California, BerkeleyBerkeley · United States2024–2026 · 14 papersEmployment 2024–2026 · PostDoc, Computer Sciencecurrent🎓ETH ZurichZurich · Switzerland2016–2026 · 11 papersEducation 2016–2018 · Master of Science, Computer ScienceEducation 2018–2024 · Ph.D., Computer Science🎓Zhejiang UniversityHangzhou · China2012–2017 · 2 papersEducation 2012–2016 · Bachelor of Engineering, Computer Science and Technology

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

🧭 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. Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation (2023 · 152 citations)
   Instruction-tuned language models often hallucinate. This paper targets one specific, checkable form: self-contradiction, where a model produces two logically incompatible statements about the same subject in the same context. Because two conflicting claims cannot both be true, such a pair always signals a factual…
2. Reasoning Models Can Be Effective Without Thinking (2025 · 58 citations)
   Large reasoning models usually write a long chain of thought before answering, and this costs many tokens and adds latency.
3. Formal Mathematical Reasoning: A New Frontier in AI (2024 · 49 citations)
   This position paper argues that informal AI-for-mathematics is approaching its limits. That approach pretrains LLMs on math text and then finetunes them on worked solutions, but its successes mostly stop around AIME-level school problems. Advanced mathematics lacks plentiful training data, and long proofs are hard to…

All works

7 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and MitigationarXiv:2305.15852Niels Mundler, Jingxuan He, Slobodan Jenko, et al.2023 · 152 citations
2. Reasoning Models Can Be Effective Without ThinkingarXiv:2504.09858Wenjie Ma, Jingxuan He, Charlie Snell, et al.2025 · 58 citations
3. Formal Mathematical Reasoning: A New Frontier in AIarXiv:2412.16075Kaiyu Yang, Gabriel Poesia, Jingxuan He, et al.2024 · 49 citations
4. Type-Constrained Code Generation with Language Models ↗arXiv:2504.09246 · no summary yetNiels Mündler et al.2025 · 16 citations
5. Progent: Securing AI Agents with Privilege Control ↗arXiv (Cornell University) · no summary yetTianneng Shi et al.2025 · 11 citations
6. Formal Reasoning Meets LLMs: Toward AI for Mathematics and Verification ↗Communications of the ACM · no summary yetKaiyu Yang et al.2026 · 1 citation
7. IDEAS: C-to-Rust Translation Using Improved Large Language Model Decoding and Automated Equivalence Testing ↗IEEE Security & Privacy · no summary yetCory T. Cornelius et al.2026

🤝 Co-authors here

11 co-authors with a page, the most papers together first.

• Charlie Snell
• Dawn Song
• Gabriel Poesia
• Kaiyu Yang
• Martin Vechev
• Matei Zaharia
• Sewon Min
• Swarat Chaudhuri
• Tyler Griggs
• Wenda Li
• Wenjie Ma

Venues

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

• Communications of the ACM
• IEEE Security & Privacy

🔗 Cited by

Papers of our library cite their works 222 times (of the 149,439 papers whose bibliographies we read); 79 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

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