--- title: "Tong Xie · UNSW Sydney — author profile and papers" description: "Tong Xie, UNSW Sydney: 4 papers on Elamur Research (2023–2025), h-index 5 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/tong-xie/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/tong-xie/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Tong Xie # Tong Xie Tong Xie has 4 papers in our library, in 2023–2025, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/); often with [Dongzhan Zhou](https://md.research.elamur.ai/free/en/authors/dongzhan-zhou/), [Wanli Ouyang](https://md.research.elamur.ai/free/en/authors/wanli-ouyang/), [Yuqiang Li](https://md.research.elamur.ai/free/en/authors/yuqiang-li/). 4 papers in our library · 2023–2025 [OpenAlex](https://openalex.org/A5017600496) · [**h-index 5**](https://openalex.org/authors/A5017600496) · [13 works](https://openalex.org/works?filter=author.id:A5017600496) · [48 citations](https://openalex.org/works?filter=author.id:A5017600496&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 4 works in our library](https://md.research.elamur.ai/free/en/authors/tong-xie/#papers) · [🔗 Cited 122 times in our library](https://md.research.elamur.ai/free/en/authors/tong-xie/cited-by/) · [⭐ Paper Stars ranking: #7203](https://md.research.elamur.ai/free/en/paper-stars/page/73/#star-7203) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Tong+Xie) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Tong+Xie) · [dblp](https://dblp.org/search?q=Tong+Xie) · [ACL Anthology](https://aclanthology.org/search/?q=Tong+Xie) ## Affiliations [🎓**UNSW Sydney** Sydney · Australia 2024–2026 · 4 papers*current*](https://md.research.elamur.ai/free/en/universities/unsw-sydney/) · [🎓**University of Georgia** Athens · United States 2021 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-of-georgia/) 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 11 The field of science this work belongs to (OpenAlex fields).[Arts and Humanities · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Language and Linguistics · 4 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Materials Science · 2 works](https://md.research.elamur.ai/free/en/shelves/materials-science/) · [Materials Chemistry · 2 works](https://md.research.elamur.ai/free/en/shelves/materials-science/materials-chemistry/) · [Computer Vision and Pattern Recognition · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Applied Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/applied-mathematics/) · [Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/mathematics/) · [Computational Theory and Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) 🧭 Topics 2 Research subjects and languages the work is about.[Language models & pretraining · 2 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/) ## Works by year ### 2020s [**2025** 1 paper](https://md.research.elamur.ai/free/en/authors/tong-xie/year/2025/) · [**2024** 2 papers](https://md.research.elamur.ai/free/en/authors/tong-xie/year/2024/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/tong-xie/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[DARWIN Series: Domain Specific Large Language Models for Natural Science](https://md.research.elamur.ai/free/en/papers/xie-2023-darwin-series-domain-specific-large/)** *(2023 · 55 citations)* General-purpose instruction-tuned LLMs perform poorly on natural science. Fine-tuned GPT models are closed and must be adapted on OpenAI's paid servers. Open alternatives are usually tuned on instructions written by GPT-3.5/GPT-4, which can reduce factual accuracy. The authors address this with DARWIN, a family of… 2. **[LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning](https://md.research.elamur.ai/free/en/papers/zhang-2024-llama-berry-pairwise-optimization-o1/)** *(2024 · 49 citations)* LLaMA-Berry is a framework that helps LLMs solve hard math problems, especially at Olympiad level, without retraining the base model. It tackles two weaknesses. Stepwise generation gets little feedback along the way. Iterative self-correction tends to stall in poor local solutions. 3. **[MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses](https://md.research.elamur.ai/free/en/papers/yang-2024-moose-chem-large-language/)** *(2024 · 36 citations)* The paper asks whether LLMs can independently propose new, valid chemistry hypotheses when given only a research background (a question and/or a short survey) from any subfield. 4. **[ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition](https://md.research.elamur.ai/free/en/papers/liu-2025-researchbench-benchmarking-llms-scientific/)** *(2025 · 25 citations)* Scientific hypothesis generation has had no dedicated benchmark for LLMs. ResearchBench addresses this by building on a decomposition from MOOSE-Chem. In that view, a hypothesis comes from combining a research background with one or more inspirations. Discovery can then be split into three sub-tasks: finding… ## Co-authors here 12 of 17 co-authors with a page, the most papers together first. - [Dongzhan Zhou](https://md.research.elamur.ai/free/en/authors/dongzhan-zhou/) ×3 - [Wanli Ouyang](https://md.research.elamur.ai/free/en/authors/wanli-ouyang/) ×3 - [Yuqiang Li](https://md.research.elamur.ai/free/en/authors/yuqiang-li/) ×3 - [Ben Gao](https://md.research.elamur.ai/free/en/authors/ben-gao/) ×2 - [Erik Cambria](https://md.research.elamur.ai/free/en/authors/erik-cambria/) ×2 - [Zonglin Yang](https://md.research.elamur.ai/free/en/authors/zonglin-yang/) ×2 - [Chunyu Kit](https://md.research.elamur.ai/free/en/authors/chunyu-kit/) - [Di Zhang](https://md.research.elamur.ai/free/en/authors/di-zhang/) - [Imran Razzak](https://md.research.elamur.ai/free/en/authors/imran-razzak/) - [Jiatong Li](https://md.research.elamur.ai/free/en/authors/jiatong-li/) - [Jinjie Ni](https://md.research.elamur.ai/free/en/authors/jinjie-ni/) - [Shixiang Tang](https://md.research.elamur.ai/free/en/authors/shixiang-tang/) ## Cited by Papers of our library cite their works 122 times (of the 149,439 papers whose bibliographies we read); [43 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/tong-xie/cited-by/). Updated 3 November 2026