Elamur Research⌕
☰
home / authors / Hengyi Cai

Hengyi Cai

Hengyi Cai has 2 papers in our library, in 2023–2026, most of them on Language models & pretraining, Reasoning, Interpretability; often with Dawei Yin, Shuaiqiang Wang, Fan Yang.

2 papers in our library · 2023–2026

OpenAlex · ORCID · Wikidata · h-index 9 · 54 works · 1,033 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 267 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #2883

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢BaiduBeijing · China2020–2026 · 26 paperscurrent🏛️Chinese Academy of SciencesBeijing · China2017–2026 · 22 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2017–2026 · 10 paperscurrent🔬Institute of High Energy PhysicsBeijing · China2024–2026 · 5 paperscurrent🔬Institute of Computing TechnologyBeijing · China2017–2025 · 13 papers🏢JingdongBeijing · China2022–2023 · 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

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

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works

🧭 Topics 3Research subjects and languages the work is about.Interpretability · 1 workLanguage models & pretraining · 1 workReasoning · 1 work

 Works by year

2020s

20261 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Explainability for Large Language Models: A Survey (2023 · 790 citations)
    Large language models work as black boxes. This opacity makes hallucinations and harmful outputs hard to diagnose and leaves users unsure how far to trust the models. The survey organizes research on explaining Transformer-based language models around how a model is adapted to a task. The first is the fine-tuning…
  2. MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching (2026 · 1 citation)
    Reinforcement learning for tool-integrated reasoning (TIR) in LLMs usually rewards whole outcomes or trajectories.

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. Explainability for Large Language Models: A SurveyACM Transactions on Intelligent Systems and TechnologyHaiyan Zhao, Hanjie Chen, Fan Yang, et al.2023 · 790 citations
  2. Tool Learning with Large Language Models: A Survey ↗arXiv:2405.17935 · no summary yetChangle Qu et al.2024 · 195 citations
  3. Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight ↗Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · no summary yetHengyi Cai et al.2020 · 86 citations
  4. MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite MatchingAnnual Meeting of the Association for Computational Linguistics (ACL)Changle Qu, Sunhao Dai, Hengyi Cai, et al.2026 · 1 citation

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 267 times (of the 149,439 papers whose bibliographies we read); 58 citing papers with a page here →.

Updated

↑ back to top

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