🧑‍🔬 Jinyan Su

🏛️ Affiliations

🎓Cornell UniversityIthaca · United States2023–2026 · 15 papersEducationcurrent🎓University of Electronic Science and Technology of ChinaChengdu · China2021–2022 · 5 papers🎓New York University Abu DhabiAbu Dhabi · United Arab Emirates2023–2024 · 4 papers🎓Wuhan UniversityWuhan · China2007–2009 · 4 papers🏢Guangdong Power Grid CompanyGuangzhou · China2025 · 2 papers🏥Kunming Children's HospitalKunming · China2021–2022 · 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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text (2023 · 172 citations)
   As LLMs improve, telling their output apart from human writing gets harder, and supervised detectors must be retrained for every new model.
2. FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial Reasoning (2026 · 10 citations)
   Current financial QA benchmarks such as FinQA and ConvFinQA mostly score the final number a model produces.
3. Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI (2026 · 5 citations)
   Earlier work suggested that people can barely tell LLM output from human writing. Most of that evidence came from English text, GPT-3.5-turbo, and small samples. This paper tests whether the claim holds for newer models, other languages and expert readers, aiming to estimate the ceiling of human detection ability.
4. The Illusion of Specialization: Unveiling the Domain-Invariant “Standing Committee” in Mixture-of-Experts Models (2026)
   Mixture-of-Experts (MoE) language models are usually thought to gain efficiency by sending different domains to different specialist experts.

All works

6 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

1. DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated TextFindings of the Association for Computational LinguisticsJinyan Su, Terry Zhuo, Di Wang, et al.2023 · 172 citations
2. M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection ↗arXiv:2305.14902 · no summary yetYuxia Wang et al.2023 · 107 citations
3. FinChain: A Symbolic Benchmark for Verifiable Chain-of-Thought Financial ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Zhuohan Xie, Daniil Orel, Rushil Thareja, et al.2026 · 10 citations
4. Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AIAnnual Meeting of the Association for Computational Linguistics (ACL)Yuxia Wang, Rui Xing, Jonibek Mansurov, et al.2026 · 5 citations
5. The Illusion of Specialization: Unveiling the Domain-Invariant “Standing Committee” in Mixture-of-Experts ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Yan Wang, Yitao Xu, Nanhan Shen, et al.2026
6. GSM-Noise: Exploring and Enhancing Large Language Models' Reasoning under Noisy Inputs ↗Findings of the Association for Computational Linguistics: ACL 2026 · no summary yetZhengxin Zhang et al.2026

🤝 Co-authors here

12 of 23 co-authors with a page, the most papers together first.

• Jimin Huang ×2
• Zhuohan Xie ×2
• Daniil Orel
• Debopriyo Banerjee
• Dhruv Sahnan
• Di Wang
• Fan Zhang
• Georgi Nenkov Georgiev
• Giovanni Puccetti
• Hachem Madmoun
• Jiahui Geng
• Jonibek Mansurov

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL) ×3: ACL 2026 ×3
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2023
• Findings of the Association for Computational Linguistics: ACL 2026

🔗 Cited by

Papers of our library cite their works 197 times (of the 149,439 papers whose bibliographies we read); 32 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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