Elamur Research⌕
☰
home / authors / Zhepei Wei

Zhepei Wei

Zhepei Wei has 3 papers in our library, in 2020–2026, most of them on Language models & pretraining, Information extraction; often with Bing Yin, Changlong Yu, Chao Zhang.

3 papers in our library · 2020–2026

OpenAlex · h-index 5 · 15 works · 712 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 150 times in our library · 1 more in our library without a page yet · ⭐ Paper Stars ranking: #2925

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

🎓Georgia Institute of TechnologyAtlanta · United States2025 · 2 paperscurrent🎓University of VirginiaCharlottesville · United States2025 · 1 papercurrent🎓Jilin UniversityChangchun · China2018–2022 · 7 papers🔬Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin UniversityChangchun Shi · China2020–2022 · 3 papers

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.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksInformation Systems · 1 work

🧭 Topics 2Research subjects and languages the work is about.Information extraction · 1 workLanguage models & pretraining · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Information extraction · 1 work

 Works by year

2020s

20261 paper20251 paper20201 paper

 Papers

The most cited first (OpenAlex and our library).

  1. A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2020 · 736 citations)
    Relational triple extraction turns sentences into (subject, relation, object) facts for knowledge graph construction.
  2. WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning (2025 · 36 citations)
    Reinforcement learning has improved LLMs mostly on single-turn problems like math. Web agents are harder to train this way: they must make long sequences of decisions on changing pages, and earlier RL approaches for this setting depended on offline or off-policy pipelines with extra components. WebAgent-R1 is a…
  3. Aligning Large Language Models via Fully Self-Synthetic Data (2026 · 2 citations)
    Preference alignment of LLMs usually depends on costly inputs: human annotations, or AI feedback from proprietary models such as GPT-4 or separately trained reward models.

All works

4 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. A Novel Cascade Binary Tagging Framework for Relational Triple ExtractionAnnual Meeting of the Association for Computational Linguistics (ACL)Zhepei Wei, Jianlin Su, Yue Wang, et al.2020 · 736 citations
  2. WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement LearningConference on Empirical Methods in Natural Language Processing (EMNLP)Zhepei Wei, Wenlin Yao, Yao Liu, et al.2025 · 36 citations
  3. The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning ↗neural information processing systems · no summary yetXinyu Zhu et al.2025 · 30 citations
  4. Aligning Large Language Models via Fully Self-Synthetic DataAnnual Meeting of the Association for Computational Linguistics (ACL)Shangjian Yin, Zhepei Wei, Xinyu Zhu, et al.2026 · 2 citations

 Co-authors here

12 of 17 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 150 times (of the 149,439 papers whose bibliographies we read); 26 citing papers with a page here →.

Updated

↑ back to top

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