--- title: "Zhengbao Jiang — author profile and papers" description: "Zhengbao Jiang, Carnegie Mellon University: 3 papers on Elamur Research (2020–2021), h-index 18 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/zhengbao-jiang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/zhengbao-jiang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Zhengbao Jiang # Zhengbao Jiang Zhengbao Jiang works on pretrained language models and on how to draw information and behaviour out of them through prompts. The papers here deal with probing the factual knowledge stored in models, with organising the fast-growing literature on prompting, and with steering abstractive summarizers through external guidance signals. The most cited paper in this collection is [Pre-train, Prompt, and Predict](https://md.research.elamur.ai/free/en/papers/liu-2021-pre-train-prompt-predict-systematic/) (2021), a survey that frames prompting as a new paradigm in which downstream tasks are recast as text for a pretrained model, and that offers a unified notation for templates, answers and their search. [How Can We Know What Language Models Know?](https://md.research.elamur.ai/free/en/papers/jiang-2020-how-can-we-know-what/) (2020) argues that a single hand-written cloze template underestimates what a masked model knows, and generates many query templates automatically by mining and paraphrasing, then combines them. The latest work in this collection, from 2021, also includes [GSum](https://md.research.elamur.ai/free/en/papers/dou-2021-gsum-general-framework-guided-neural/), a framework that conditions a pretrained encoder-decoder on the source document together with a separate guidance signal, so that different kinds of guidance, such as keywords, relations or highlighted sentences, can be compared within one model. Jiang's papers are affiliated with [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/), with earlier work at [Renmin University of China](https://md.research.elamur.ai/free/en/universities/renmin-university-of-china/). The most frequent co-author is [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/), followed by [Pengfei Liu](https://md.research.elamur.ai/free/en/authors/pengfei-liu/) and [Hiroaki Hayashi](https://md.research.elamur.ai/free/en/authors/hiroaki-hayashi/). The topics are [language models and pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) and [summarization](https://md.research.elamur.ai/free/en/topics/summarization/). Zhengbao Jiang has 3 papers in our library, in 2020–2021, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Summarization](https://md.research.elamur.ai/free/en/topics/summarization/); often with [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/), [Hiroaki Hayashi](https://md.research.elamur.ai/free/en/authors/hiroaki-hayashi/), [Pengfei Liu](https://md.research.elamur.ai/free/en/authors/pengfei-liu/). 3 papers in our library · 2020–2021 current affiliation [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · Pittsburgh United States [OpenAlex](https://openalex.org/A5043295774) · [ORCID](https://orcid.org/0000-0002-0315-6727) · [**h-index 18**](https://openalex.org/authors/A5043295774) · [39 works](https://openalex.org/works?filter=author.id:A5043295774) · [6,902 citations](https://openalex.org/works?filter=author.id:A5043295774&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [3 works in our library](https://md.research.elamur.ai/free/en/authors/zhengbao-jiang/#papers) · [1,879 citations in our library](https://md.research.elamur.ai/free/en/authors/zhengbao-jiang/cited-by/) · 3 more works in our library · [⭐ Paper Star rank #315](https://md.research.elamur.ai/free/en/paper-stars/page/4/#star-315) 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=Zhengbao+Jiang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Zhengbao+Jiang) · [dblp](https://dblp.org/search?q=Zhengbao+Jiang) · [ACL Anthology](https://aclanthology.org/search/?q=Zhengbao+Jiang) ## Affiliations [🎓**Carnegie Mellon University** Pittsburgh · United States 2019–2024 · 29 papers*current*](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🎓**Renmin University of China** Beijing · China 2015–2018 · 5 papers](https://md.research.elamur.ai/free/en/universities/renmin-university-of-china/) · [🎓**University College London** London · United Kingdom 2022 · 2 papers](https://md.research.elamur.ai/free/en/universities/university-college-london/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 10 more institutions on single bylines are not listed. ## Topics [Language models & pretraining 2](https://md.research.elamur.ai/free/en/topics/language-models/) · [Summarization 1](https://md.research.elamur.ai/free/en/topics/summarization/) ## Works by year ### 2020s [**2021** 2 papers](https://md.research.elamur.ai/free/en/authors/zhengbao-jiang/year/2021/) · [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/jiang-2020-how-can-we-know-what/) ## Papers The most cited first (OpenAlex and our library). 1. **[Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/papers/liu-2021-pre-train-prompt-predict-systematic/)** *(2021 · 5,375 citations)* This survey maps a fast-growing area of NLP in which pre-trained language models handle downstream tasks by recasting the task input as text. 2. **[How Can We Know What Language Models Know?](https://md.research.elamur.ai/free/en/papers/jiang-2020-how-can-we-know-what/)** *(2020 · 1,493 citations)* Factual probing of masked language models usually relies on a single cloze template written by hand. If the model learned a fact from text phrased differently, that template can miss it, so reported scores only give a lower bound on what the model knows. The authors try to raise this bound by generating query… 3. **[GSum: A General Framework for Guided Neural Abstractive Summarization](https://md.research.elamur.ai/free/en/papers/dou-2021-gsum-general-framework-guided-neural/)** *(2021 · 317 citations)* Abstractive summarizers write fluent text, but they can introduce facts not found in the source and are hard to steer. ## 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 8 co-authors with a page, the most papers together first. - [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/) ×3 - [Hiroaki Hayashi](https://md.research.elamur.ai/free/en/authors/hiroaki-hayashi/) ×2 - [Pengfei Liu](https://md.research.elamur.ai/free/en/authors/pengfei-liu/) ×2 - [Frank F. Xu](https://md.research.elamur.ai/free/en/authors/frank-f-xu/) - [Jinlan Fu](https://md.research.elamur.ai/free/en/authors/jinlan-fu/) - [Jun Araki](https://md.research.elamur.ai/free/en/authors/jun-araki/) - [Weizhe Yuan](https://md.research.elamur.ai/free/en/authors/weizhe-yuan/) - [Zi-Yi Dou](https://md.research.elamur.ai/free/en/authors/zi-yi-dou/) ## Cited by Papers of our library cite their works 1,879 times (of the 140,884 papers whose bibliographies we read); [140 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/zhengbao-jiang/cited-by/).