--- title: "Zhiyong Lu — author profile and papers" description: "Zhiyong Lu, National Institutes of Health: 2 papers on Elamur Research (2019–2024), h-index 82 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/zhiyong-lu/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/zhiyong-lu/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Zhiyong Lu # Zhiyong Lu Zhiyong Lu works on biomedical natural language processing, with a focus on how to measure what language models can do with medical and scientific text. Both papers here build shared evaluation resources. They gather existing datasets into a common test so that different models and system designs can be compared on equal terms. The tasks covered range from [information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/) over research articles and clinical notes to [information retrieval and search](https://md.research.elamur.ai/free/en/topics/information-retrieval/) in support of answering medical questions. The most cited of these papers, [Transfer Learning in Biomedical Natural Language Processing](https://md.research.elamur.ai/free/en/papers/peng-2019-transfer-learning-biomedical-natural-language/) (2019), addressed a practical problem. Biomedical text models were hard to compare because each study had tested them on its own set of corpora. The paper introduced BLUE, a benchmark modeled on GLUE. It brings together ten shared-task corpora covering five kinds of task, among them named entity recognition, relation extraction, sentence similarity, document classification and inference. The paper also reports baseline results from fine-tuned BERT and ELMo models. The later work turns to large language models. [Benchmarking Retrieval-Augmented Generation for Medicine](https://md.research.elamur.ai/free/en/papers/xiong-2024-benchmarking-retrieval-augmented-generation-medicine/) (2024) asks which combination of document collection, retriever and underlying model works best when retrieval is used to reduce confident mistakes and outdated answers in medical question answering. It presents MIRAGE, a set of 7,663 multiple-choice questions drawn from five biomedical QA datasets. In MIRAGE, retrieval is given only the question and never the answer choices. The paper also releases MedRAG, a toolkit for assembling and testing such pipelines, and compares 41 configurations. Among Lu's co-authors here is [Qiao Jin](https://md.research.elamur.ai/free/en/authors/qiao-jin/). Lu is based at the National Center for Biotechnology Information, part of the [United States National Library of Medicine](https://md.research.elamur.ai/free/en/labs/united-states-national-library-of-medicine/) at the [National Institutes of Health](https://md.research.elamur.ai/free/en/government/national-institutes-of-health/) in Bethesda. Lu's bylines have carried these affiliations since 2008. Zhiyong Lu has 2 papers in our library, in 2019–2024, most of them on [Information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/), [Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/); often with [Qiao Jin](https://md.research.elamur.ai/free/en/authors/qiao-jin/). 2 papers in our library · 2019–2024 current affiliation [National Institutes of Health](https://md.research.elamur.ai/free/en/government/national-institutes-of-health/) · Bethesda United States; [State Administration of Cultural Heritage](https://ror.org/04d0vc473) · Beijing China; [United States National Library of Medicine](https://md.research.elamur.ai/free/en/labs/united-states-national-library-of-medicine/) · Bethesda United States; [National Center for Biotechnology Information](https://ror.org/02meqm098) · Bethesda United States; [Shaanxi History Museum](https://ror.org/04fyt3464) · Yanta China [OpenAlex](https://openalex.org/A5083081872) · [ORCID](https://orcid.org/0000-0001-9998-916X) · [Wikidata](https://www.wikidata.org/wiki/Q19857266) · [**h-index 82**](https://openalex.org/authors/A5083081872) · [424 works](https://openalex.org/works?filter=author.id:A5083081872) · [33,473 citations](https://openalex.org/works?filter=author.id:A5083081872&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/zhiyong-lu/#papers) · [404 citations in our library](https://md.research.elamur.ai/free/en/authors/zhiyong-lu/cited-by/) · 3 more works in our library · [⭐ Paper Star rank #1513](https://md.research.elamur.ai/free/en/paper-stars/page/16/#star-1513) 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=Zhiyong+Lu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Zhiyong+Lu) · [dblp](https://dblp.org/search?q=Zhiyong+Lu) · [ACL Anthology](https://aclanthology.org/search/?q=Zhiyong+Lu) ## Affiliations [🏛️**National Institutes of Health** Bethesda · United States 2008–2026 · 261 papers*current**employment (Wikidata)*](https://md.research.elamur.ai/free/en/government/national-institutes-of-health/) · [🔬**National Center for Biotechnology Information** Bethesda · United States 2008–2026 · 260 papers*current*](https://ror.org/02meqm098) · [🔬**United States National Library of Medicine** Bethesda · United States 2008–2026 · 90 papers*current*](https://md.research.elamur.ai/free/en/labs/united-states-national-library-of-medicine/) · [🔬**Shaanxi History Museum** Yanta · China 2024–2026 · 2 papers*current*](https://ror.org/04fyt3464) · [🏛️**State Administration of Cultural Heritage** Beijing · China 2024–2026 · 2 papers*current*](https://ror.org/04d0vc473) · [🎓**Wuhan University of Technology** Wuhan · China 2008–2015 · 11 papers](https://ror.org/03fe7t173) · [🎓**University of Colorado Anschutz** Aurora · United States 2005–2013 · 8 papers](https://ror.org/03wmf1y16) · [🎓**University of Colorado Denver** Denver · United States 2005–2013 · 5 papers](https://md.research.elamur.ai/free/en/universities/university-of-colorado-denver/) · [🎓**National University of Defense Technology** Changsha · China 2010–2014 · 3 papers](https://md.research.elamur.ai/free/en/universities/national-university-of-defense-technology/) · [🎓**University of Delaware** Newark · United States 2012–2014 · 3 papers](https://md.research.elamur.ai/free/en/universities/university-of-delaware/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 40 more institutions on single bylines are not listed. ## Topics [Information extraction 1](https://md.research.elamur.ai/free/en/topics/information-extraction/) · [Information retrieval & search 1](https://md.research.elamur.ai/free/en/topics/information-retrieval/) ## Works by year ### 2020s [**2024** 1 paper](https://md.research.elamur.ai/free/en/papers/xiong-2024-benchmarking-retrieval-augmented-generation-medicine/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/peng-2019-transfer-learning-biomedical-natural-language/) ## Papers The most cited first (OpenAlex and our library). 1. **[Transfer Learning in Biomedical Natural Language Processing: An Evaluation of BERT and ELMo on Ten Benchmarking Datasets](https://md.research.elamur.ai/free/en/papers/peng-2019-transfer-learning-biomedical-natural-language/)** *(2019 · 1,070 citations)* Biomedical language representation models such as BioBERT or clinical BERT were hard to compare, because each study reported results on its own choice of datasets or on differently sized versions of the same ones. 2. **[Benchmarking Retrieval-Augmented Generation for Medicine](https://md.research.elamur.ai/free/en/papers/xiong-2024-benchmarking-retrieval-augmented-generation-medicine/)** *(2024 · 426 citations)* Large language models answer medical questions well, but they can produce confident errors and miss recent clinical knowledge. ## Also in our library 3 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 1 co-author with a page, the most papers together first. - [Qiao Jin](https://md.research.elamur.ai/free/en/authors/qiao-jin/) ## Cited by Papers of our library cite their works 404 times (of the 140,884 papers whose bibliographies we read); [15 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/zhiyong-lu/cited-by/).