Elamur Research⌕
☰
home / authors / Zhengyang Tang

Zhengyang Tang

Zhengyang Tang has 2 papers in our library, in 2024–2025, most of them on Language models & pretraining, Evaluation & benchmarks, Semitic languages; often with Bang An, Benyou Wang, Bofei Gao.

2 papers in our library · 2024–2025

OpenAlex · h-index 16 · 75 works · 921 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 312 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #5934

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

🏢China Yangtze Power Co., Ltd.Wuhan · China2019–2026 · 37 paperscurrent🎓Chinese University of Hong Kong, ShenzhenShenzhen · China2022–2026 · 6 paperscurrent🎓Harbin Institute of TechnologyHarbin · China2026 · 1 papercurrent🎓Huazhong University of Science and TechnologyWuhan · China2021–2025 · 7 papers🎓Northeast Forestry UniversityHarbin · China2024–2025 · 6 papers🎓Chinese University of Hong KongHong Kong · China2024–2025 · 3 papers🎓Shenzhen Research Institute of Big DataShenzhen · China2024–2025 · 3 papers🎓Sun Yat-sen UniversityGuangzhou · China2025 · 3 papers🎓Southwestern University of Finance and EconomicsChengdu · China2023–2024 · 3 papers🎓Wuhan UniversityWuhan · China2022 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 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.

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksMathematics · 1 workApplied Mathematics · 1 workComputational Theory and Mathematics · 1 work

🧭 Topics 4Research subjects and languages the work is about.Language models & pretraining · 2 worksEvaluation & benchmarks · 1 workGrammatical error correction & learner language · 1 workSemitic languages · 1 work

 Works by year

2020s

20251 paper20241 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models (2024 · 163 citations)
    Widely used math benchmarks such as GSM8K and MATH are close to saturated. OpenAI o1 scores about 95% on MATH, so these tests no longer separate the strongest LLMs well. The authors built Omni-MATH, a text-only benchmark of 4,428 competition problems. They range from introductory contests (CEMC, HMMT) up to IMO…
  2. Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion (2025 · 11 citations)
    English-centric LLMs such as LLaMA2 handle Arabic poorly at the vocabulary level. Their tokenizer holds little beyond basic Arabic characters, so Arabic text splits into near-letter sequences and generation is slow. Adding many Arabic subwords at once is risky: suddenly the model sees many units it has no trained…

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. Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language ModelsarXiv:2410.07985Bofei Gao, Feifan Song, Zhe Yang, et al.2024 · 163 citations
  2. MathScale: Scaling Instruction Tuning for Mathematical Reasoning ↗arXiv:2403.02884 · no summary yetZhengyang Tang et al.2024 · 83 citations
  3. Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models ↗arXiv:2402.13064 · no summary yetHaoran Li et al.2024 · 65 citations
  4. Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary ExpansionAnnual Meeting of the Association for Computational Linguistics (ACL)Jianqing Zhu, Huang Huang, Zhihang Lin, et al.2025 · 11 citations

 Co-authors here

12 of 20 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 312 times (of the 149,439 papers whose bibliographies we read); 91 citing papers with a page here →.

Updated

↑ back to top

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