--- title: "Rui Zheng — author profile and papers" description: "Rui Zheng, Hebei University of Engineering: 3 papers on Elamur Research (2023), h-index 34 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/rui-zheng/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/rui-zheng/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Rui Zheng # Rui Zheng Rui Zheng works on large language models, in particular how they are trained, aligned and applied. Zheng's papers here, all from 2023, take up three linked questions: how to make reinforcement learning from human feedback work reliably, how to teach one model to handle many information extraction tasks through instructions, and how language models can serve as the core of general-purpose agents. The methods range from careful training experiments to multi-task instruction tuning and a broad survey of the literature. The most cited work is [The Rise and Potential of Large Language Model Based Agents](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/), a survey from 2023. It follows the idea of an agent from philosophy into AI, argues that a language model is a fitting central controller, and sorts existing studies into a modular framework. [InstructUIE](https://md.research.elamur.ai/free/en/papers/wang-2023-instructuie-multi-task-instruction-tuning/) addresses the weak extraction scores of prompted models. It trains a single model on many extraction tasks through instruction tuning, so that it does not need separate fine-tuning for each task. The newest papers here, also from 2023, turn toward alignment. [Secrets of RLHF in Large Language Models Part I: PPO](https://md.research.elamur.ai/free/en/papers/zheng-2023-secrets-rlhf-large-language-models/) breaks the feedback pipeline into its stages and tests how implementation choices shape the PPO stage. It finds that reward and loss curves are poor guides to whether training is going well. Watching the model's perplexity, the length of its answers and how far it drifts from the supervised starting point gives earlier warning of trouble. The agent survey and the PPO report both come from the Fudan NLP Group, and bylines from 2022 to 2025 list [Fudan University](https://md.research.elamur.ai/free/en/universities/fudan-university/). Bylines from 2025 onward list Jinan University and Hebei University of Engineering. Co-authors include [Senjie Jin](https://md.research.elamur.ai/free/en/authors/senjie-jin/), [Tao Gui](https://md.research.elamur.ai/free/en/authors/tao-gui/) and [Qi Zhang](https://md.research.elamur.ai/free/en/authors/qi-zhang/). The papers fall under [language models and pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) and [information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/). Rui Zheng has 3 papers in our library, in 2023, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Information extraction](https://md.research.elamur.ai/free/en/topics/information-extraction/); often with [Senjie Jin](https://md.research.elamur.ai/free/en/authors/senjie-jin/), [Ming Zhang](https://md.research.elamur.ai/free/en/authors/ming-zhang/), [Qi Zhang](https://md.research.elamur.ai/free/en/authors/qi-zhang/). 3 papers in our library · 2023 current affiliation [Hebei University of Engineering](https://ror.org/036h65h05), Handan, China; [Jinan University](https://ror.org/02xe5ns62), Guangzhou, China; [Ningxia University](https://ror.org/04j7b2v61), Yinchuan, China; [Children's Hospital of Zhejiang University](https://ror.org/025fyfd20), Hangzhou, China; [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/), Hangzhou, China [OpenAlex](https://openalex.org/A5055879965) · [ORCID](https://orcid.org/0000-0002-4225-7133) · [**h-index 34**](https://openalex.org/authors/A5055879965) · [143 works](https://openalex.org/works?filter=author.id:A5055879965) · [3 616 citations](https://openalex.org/works?filter=author.id:A5055879965&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works in our library](https://md.research.elamur.ai/free/en/authors/rui-zheng/#papers) · [618 citations in our library](https://md.research.elamur.ai/free/en/authors/rui-zheng/cited-by/) · 1 more work in our library · [⭐ Paper Star rank #1445](https://md.research.elamur.ai/free/en/paper-stars/page/15/#star-1445) 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=Rui+Zheng) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Rui+Zheng) · [dblp](https://dblp.org/search?q=Rui+Zheng) · [ACL Anthology](https://aclanthology.org/search/?q=Rui+Zheng) ## Affiliations - [Hebei University of Engineering](https://ror.org/036h65h05) · Handan, China —current · 2025–2026 on 2 papers - [Jinan University](https://ror.org/02xe5ns62) · Guangzhou, China —current · 2025–2026 on 2 papers - [Children's Hospital of Zhejiang University](https://ror.org/025fyfd20) · Hangzhou, China —current · 2026 on 1 paper - [Ningxia University](https://ror.org/04j7b2v61) · Yinchuan, China —current · 2026 on 1 paper - [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) · Hangzhou, China —current · 2026 on 1 paper - [Fudan University](https://md.research.elamur.ai/free/en/universities/fudan-university/) · Shanghai, China —2022–2025 on 14 papers - [Yantai University](https://ror.org/01rp41m56) · Yantai, China —2023–2025 on 12 papers - [Qingdao University of Technology](https://ror.org/01qzc0f54) · Qingdao, China —2022–2025 on 8 papers - [China National Petroleum Corporation (China)](https://ror.org/05269d038) · Beijing, China —2020–2025 on 7 papers - [Guangzhou University](https://ror.org/05ar8rn06) · Guangzhou, China —2024–2025 on 3 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 43 more institutions on single bylines are not listed. ## Topics [Language models & pretraining 2](https://md.research.elamur.ai/free/en/topics/language-models/) · [Information extraction 1](https://md.research.elamur.ai/free/en/topics/information-extraction/) ## Works by year ### 2020s [**2023** 3 papers](https://md.research.elamur.ai/free/en/authors/rui-zheng/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[The Rise and Potential of Large Language Model Based Agents: A Survey](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/)** *(2023 · 1 262 citations)* Earlier AI-agent research mostly refined algorithms or training schemes for narrow skills such as Go or chess. 2. **[InstructUIE: Multi-task Instruction Tuning for Unified Information Extraction](https://md.research.elamur.ai/free/en/papers/wang-2023-instructuie-multi-task-instruction-tuning/)** *(2023 · 194 citations)* Large language models handle many tasks well when given prompts, but they still struggle with information extraction (IE). 3. **[Secrets of RLHF in Large Language Models Part I: PPO](https://md.research.elamur.ai/free/en/papers/zheng-2023-secrets-rlhf-large-language-models/)** *(2023 · 130 citations)* RLHF is the main way to make LLMs helpful, honest and harmless. Its PPO stage, though, is unstable, sensitive to hyperparameters and costly to debug, and few open implementations existed. This report from the Fudan NLP Group and ByteDance breaks the RLHF pipeline into its stages: SFT, reward model training, and PPO… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 8 co-authors with a page, the most papers together first. - [Senjie Jin](https://md.research.elamur.ai/free/en/authors/senjie-jin/) ×2 - [Ming Zhang](https://md.research.elamur.ai/free/en/authors/ming-zhang/) - [Qi Zhang](https://md.research.elamur.ai/free/en/authors/qi-zhang/) - [Tao Gui](https://md.research.elamur.ai/free/en/authors/tao-gui/) - [Wei He](https://md.research.elamur.ai/free/en/authors/wei-he/) - [Wei Shen](https://md.research.elamur.ai/free/en/authors/wei-shen/) - [Xiao Wang](https://md.research.elamur.ai/free/en/authors/xiao-wang/) - [Yan Liu](https://md.research.elamur.ai/free/en/authors/yan-liu/) ## Cited by Papers of our library cite their works 618 times (of the 140 884 papers whose bibliographies we read); [34 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/rui-zheng/cited-by/).