--- title: "Yichong Xu — author profile and papers" description: "Yichong Xu, Microsoft: 2 papers on Elamur Research (2021–2022), h-index 16 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/yichong-xu/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yichong-xu/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Yichong Xu # Yichong Xu Yichong Xu has 2 papers in our library, in 2021–2022, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Information retrieval & search](https://md.research.elamur.ai/free/en/topics/information-retrieval/); often with [Chenguang Zhu](https://md.research.elamur.ai/free/en/authors/chenguang-zhu/), [Michael Zeng](https://md.research.elamur.ai/free/en/authors/michael-zeng/), [Shuohang Wang](https://md.research.elamur.ai/free/en/authors/shuohang-wang/). 2 papers in our library · 2021–2022 [OpenAlex](https://openalex.org/A5006654661) · [ORCID](https://orcid.org/0000-0002-1302-738X) · [**h-index 16**](https://openalex.org/authors/A5006654661) · [44 works](https://openalex.org/works?filter=author.id:A5006654661) · [1,960 citations](https://openalex.org/works?filter=author.id:A5006654661&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/yichong-xu/#papers) · [🔗 391 citations in our library](https://md.research.elamur.ai/free/en/authors/yichong-xu/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Star rank #2753](https://md.research.elamur.ai/free/en/paper-stars/page/28/#star-2753) 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=Yichong+Xu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Yichong+Xu) · [dblp](https://dblp.org/search?q=Yichong+Xu) · [ACL Anthology](https://aclanthology.org/search/?q=Yichong+Xu) ## Affiliations [🏢**Microsoft** Redmond · United States 2017–2024 · 18 papers*current*](https://md.research.elamur.ai/free/en/companies/microsoft/) · [🎓**Carnegie Mellon University** Pittsburgh · United States 2017–2020 · 13 papers](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. ## Topics [Language models & pretraining (2)](https://md.research.elamur.ai/free/en/topics/language-models/) · [Information retrieval & search (1)](https://md.research.elamur.ai/free/en/topics/information-retrieval/) ## Works by year ### 2020s [**2022** 1 paper](https://md.research.elamur.ai/free/en/papers/yu-2022-generate-rather-than-retrieve-large/) · [**2021** 1 paper](https://md.research.elamur.ai/free/en/papers/wang-2021-want-reduce-labeling-cost-gpt/) ## Papers The most cited first (OpenAlex and our library). 1. **[Want To Reduce Labeling Cost? GPT-3 Can Help](https://md.research.elamur.ai/free/en/papers/wang-2021-want-reduce-labeling-cost-gpt/)** *(2021 · 298 citations)* Manual annotation for NLP is slow and expensive. Most pseudo-labeling methods are tied to one task and need a sizable labeled seed set. This paper asks whether GPT-3 can serve as a cheap annotator whose outputs train smaller deployable models, as an alternative to running the huge model itself. The authors prompt… 2. **[Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://md.research.elamur.ai/free/en/papers/yu-2022-generate-rather-than-retrieve-large/)** *(2022 · 280 citations)* Open-domain QA and other knowledge-heavy tasks usually use a retrieve-then-read setup. A retriever such as DPR pulls fixed-size passages from Wikipedia, and a reader picks out the answer. The authors argue that these passages are often noisy and that two-tower retrievers model the question and the document only… ## Also in our library 2 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 8 co-authors with a page, the most papers together first. - [Chenguang Zhu](https://md.research.elamur.ai/free/en/authors/chenguang-zhu/) ×2 - [Michael Zeng](https://md.research.elamur.ai/free/en/authors/michael-zeng/) ×2 - [Shuohang Wang](https://md.research.elamur.ai/free/en/authors/shuohang-wang/) ×2 - [Dan Iter](https://md.research.elamur.ai/free/en/authors/dan-iter/) - [Meng Jiang](https://md.research.elamur.ai/free/en/authors/meng-jiang/) - [Soumya Sanyal](https://md.research.elamur.ai/free/en/authors/soumya-sanyal/) - [Wenhao Yu](https://md.research.elamur.ai/free/en/authors/wenhao-yu/) - [Yang Liu](https://md.research.elamur.ai/free/en/authors/yang-liu/) ## Cited by Papers of our library cite their works 391 times (of the 140,884 papers whose bibliographies we read); [43 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/yichong-xu/cited-by/).