--- title: "Chong Zhang — author profile and papers" description: "Chong Zhang, Beijing Information Science & Technology University: 2 papers on Elamur Research (2022), h-index 25 — affiliations, topics, co-authors and…" canonical: "https://research.elamur.ai/free/en/authors/chong-zhang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/chong-zhang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Chong Zhang # Chong Zhang Chong Zhang's papers here deal with large language models and how to make their behaviour more useful and safer once deployed. Both works in our library date from 2022 and fall under [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/). They address two practical questions: how to bring a model's outputs closer to what users actually ask for, and how to catch harmful content. The methods rest on human annotation, learned reward models and classifiers, and examples taken from real production use. The most cited of these is [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). It adapted GPT-3 in stages. First it fine-tuned the model on answers written by hired labelers. It then trained a reward model on the labelers' rankings of alternative responses and optimised the model against it with reinforcement learning, the approach known as RLHF. The second paper, [A Holistic Approach to Undesired Content Detection in the Real World](https://md.research.elamur.ai/free/en/papers/markov-2022-holistic-approach-undesired-content-detection/), describes a complete pipeline for moderation classifiers rather than a single modelling idea. It defines a taxonomy of unwanted content with severity levels, sets annotation guidelines refined through calibration with labelers, and gathers training examples iteratively from live traffic with personal information masked. Because both papers appeared in the same year, they show one line of work rather than a shift in direction. That line concerns alignment and content safety for models in real use, and both papers come from author groups at OpenAI. Co-authors include [Long Ouyang](https://md.research.elamur.ai/free/en/authors/long-ouyang/), [John Schulman](https://md.research.elamur.ai/free/en/authors/john-schulman/), [Jeff Wu](https://md.research.elamur.ai/free/en/authors/jeff-wu/) and [Lilian Weng](https://md.research.elamur.ai/free/en/authors/lilian-weng/), while [Sandhini Agarwal](https://md.research.elamur.ai/free/en/authors/sandhini-agarwal/) appears on both of Zhang's papers here. Zhang's current institution is Beijing Information Science & Technology University. Chong Zhang has 2 papers in our library, in 2022, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Sandhini Agarwal](https://md.research.elamur.ai/free/en/authors/sandhini-agarwal/), [Alex Ray](https://md.research.elamur.ai/free/en/authors/alex-ray/), [Diogo Almeida](https://md.research.elamur.ai/free/en/authors/diogo-almeida/). 2 papers in our library · 2022 current affiliation [Beijing Information Science & Technology University](https://ror.org/04xnqep60), Beijing, China [OpenAlex](https://openalex.org/A5100393899) · [ORCID](https://orcid.org/0000-0002-2162-4344) · [**h-index 25**](https://openalex.org/authors/A5100393899) · [166 works](https://openalex.org/works?filter=author.id:A5100393899) · [7 940 citations](https://openalex.org/works?filter=author.id:A5100393899&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/chong-zhang/#papers) · [6 912 citations in our library](https://md.research.elamur.ai/free/en/authors/chong-zhang/cited-by/) · [⭐ Paper Star rank #426](https://md.research.elamur.ai/free/en/paper-stars/page/5/#star-426) 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=Chong+Zhang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Chong+Zhang) · [dblp](https://dblp.org/search?q=Chong+Zhang) · [ACL Anthology](https://aclanthology.org/search/?q=Chong+Zhang) ## Affiliations - [Beijing Information Science & Technology University](https://ror.org/04xnqep60) · Beijing, China —current · 2018–2026 on 2 papers - [Alibaba Group (China)](https://md.research.elamur.ai/free/en/companies/alibaba-group/) · Hangzhou, China —2013–2025 on 15 papers - [Tencent (China)](https://md.research.elamur.ai/free/en/companies/tencent/) · Shenzhen, China —2020–2025 on 11 papers - [Deakin University](https://ror.org/02czsnj07) · Burwood, Australia —2020–2025 on 4 papers - [Ocean University of China](https://ror.org/04rdtx186) · Qingdao, China —2025 on 2 papers - [Xi’an Jiaotong-Liverpool University](https://md.research.elamur.ai/free/en/universities/xi-an-jiaotong-liverpool-university/) · Suzhou, China —2023–2024 on 5 papers - [Alibaba Group (Cayman Islands)](https://md.research.elamur.ai/free/en/companies/alibaba-group-cayman-islands/) · George Town, Cayman Islands —2023–2024 on 4 papers - [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) · Beijing, China —2021–2024 on 3 papers - [State Key Laboratory of Software Development Environment](https://md.research.elamur.ai/free/en/labs/state-key-laboratory-of-software-development-environment/) · Beijing —2021–2024 on 3 papers - [Alibaba DAMO Academy (China)](https://md.research.elamur.ai/free/en/companies/alibaba-damo-academy/) · Hangzhou, China —2023–2024 on 2 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 52 more institutions on single bylines are not listed. ## Topics [Language models & pretraining 1](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2022** 2 papers](https://md.research.elamur.ai/free/en/authors/chong-zhang/year/2022/) ## Papers The most cited first (OpenAlex and our library). 1. **[Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/)** *(2022 · 5 770 citations)* Making language models larger does not by itself make them more helpful: they make up facts, generate toxic text, or disregard the user's request. 2. **[A Holistic Approach to Undesired Content Detection in the Real World](https://md.research.elamur.ai/free/en/papers/markov-2022-holistic-approach-undesired-content-detection/)** *(2022 · 254 citations)* Moderating the inputs and outputs of language models requires classifiers that cover many kinds of undesired content and that still work on real production traffic. ## Co-authors here 12 co-authors with a page, the most papers together first. - [Sandhini Agarwal](https://md.research.elamur.ai/free/en/authors/sandhini-agarwal/) ×2 - [Alex Ray](https://md.research.elamur.ai/free/en/authors/alex-ray/) - [Diogo Almeida](https://md.research.elamur.ai/free/en/authors/diogo-almeida/) - [Jacob Hilton](https://md.research.elamur.ai/free/en/authors/jacob-hilton/) - [Jeff Wu](https://md.research.elamur.ai/free/en/authors/jeff-wu/) - [John Schulman](https://md.research.elamur.ai/free/en/authors/john-schulman/) - [Lilian Weng](https://md.research.elamur.ai/free/en/authors/lilian-weng/) - [Long Ouyang](https://md.research.elamur.ai/free/en/authors/long-ouyang/) - [Pamela Mishkin](https://md.research.elamur.ai/free/en/authors/pamela-mishkin/) - [Steven Adler](https://md.research.elamur.ai/free/en/authors/steven-adler/) - [Teddy Lee](https://md.research.elamur.ai/free/en/authors/teddy-lee/) - [Xu Jiang](https://md.research.elamur.ai/free/en/authors/xu-jiang/) ## Cited by Papers of our library cite their works 6 912 times (of the 140 884 papers whose bibliographies we read); [483 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/chong-zhang/cited-by/).