Elamur Research⌕
☰
home / authors / Xingxuan Li

Xingxuan Li

Xingxuan Li has 2 papers in our library, in 2023, most of them on Language models & pretraining, Reasoning; often with Chengwei Qin, Chenhui Shen, Guanzheng Chen.

2 papers in our library · 2023

OpenAlex · h-index 8 · 21 works · 329 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 285 times in our library · 3 more in our library without a page yet · ⭐ Paper Stars ranking: #4491

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

🎓Nanyang Technological UniversitySingapore · Singapore2022–2025 · 15 papers🏢Alibaba DAMO AcademyHangzhou · China2023–2025 · 6 papers🏢Alibaba GroupHangzhou · China2023–2025 · 6 papers🏢Alibaba GroupGeorge Town · Cayman Islands2023–2025 · 3 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.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksComputer Vision and Pattern Recognition · 1 work

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

 Works by year

2020s

20232 papersXingxuan Li's papers of 2023

 Papers

The most cited first (OpenAlex and our library).

  1. Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought Framework (2023 · 144 citations)
    Large language models often invent facts. Chain-of-Thought (CoT) prompting makes their reasoning visible, but it does not fix this weakness on knowledge-heavy tasks. The authors propose Verify-and-Edit (VE), a framework built on GPT-3 that repairs reasoning chains after they are generated, rather than only choosing…
  2. SeaLLMs — Large Language Models for Southeast Asia (2023 · 92 citations)
    Mainstream LLMs are trained mostly on English. As a result, they handle Southeast Asian languages poorly, especially those written in non-Latin scripts, which standard BPE tokenizers break into very long token sequences. SeaLLMs are open models for Southeast Asian languages, built by adapting English-centric…

All works

5 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. Verify-and-Edit: A Knowledge-Enhanced Chain-of-Thought FrameworkAnnual Meeting of the Association for Computational Linguistics (ACL)Ruochen Zhao, Xingxuan Li, Shafiq Joty, et al.2023 · 144 citations
  2. Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources ↗arXiv:2305.13269 · no summary yetXingxuan Li et al.2023 · 110 citations
  3. SeaLLMs — Large Language Models for Southeast AsiaarXiv:2312.00738Xuan-Phi Nguyen, Wenxuan Zhang, Xin Li, et al.2023 · 92 citations
  4. Can We Further Elicit Reasoning in LLMs? Critic-Guided Planning with Retrieval-Augmentation for Solving Challenging Tasks ↗Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yetXingxuan Li et al.2025 · 13 citations
  5. 100 Days After DeepSeek-R1: A Survey on Replication Studies and More Directions for Reasoning Language Models ↗arXiv:2505.00551 · no summary yetChong Zhang et al.2025 · 9 citations

 Co-authors here

12 of 13 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 285 times (of the 141,840 papers whose bibliographies we read); 28 citing papers with a page here →.

Updated

↑ back to top

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