--- title: "Chunting Zhou — author profile and papers" description: "Chunting Zhou, Wenzhou Medical University: 6 papers on Elamur Research (2019–2023), h-index 18 — affiliations, topics, co-authors and who cites them in…" canonical: "https://research.elamur.ai/free/en/authors/chunting-zhou/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/chunting-zhou/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Chunting Zhou # Chunting Zhou Chunting Zhou works in natural language processing, mainly on neural text generation and large language models. Their papers here return to a few questions: how to adapt a big pretrained model without retraining all of its weights, how to tell when generated text says something its source does not support, and how to translate well when parallel data is scarce. The work typically tests these ideas on translation and summarization benchmarks, and more recently by prompting large generative models. The most cited paper here, [Towards a Unified View of Parameter-Efficient Transfer Learning](https://md.research.elamur.ai/free/en/papers/he-2021-towards-unified-view-parameter-efficient/) (2021), treats adapters, prefix tuning, prompt tuning and LoRA as variants of a single idea: a learned change applied to selected hidden states of a frozen network. It then compares these methods along a small set of design choices. Also from 2021, [Detecting Hallucinated Content in Conditional Neural Sequence Generation](https://md.research.elamur.ai/free/en/papers/zhou-2021-detecting-hallucinated-content-conditional-neural/) proposes marking each output token as faithful or hallucinated, using nothing but the source and the generated text. [In-context Examples Selection for Machine Translation](https://md.research.elamur.ai/free/en/papers/agrawal-2023-context-examples-selection-machine-translation/) (2023) shows that the demonstrations placed in a prompt matter a great deal. One noisy, unrelated example can badly damage translation output, while a carefully chosen one helps. The newest papers, all from 2023, move toward checking and aligning large language models. [FacTool](https://md.research.elamur.ai/free/en/papers/chern-2023-factool-factuality-detection-generative-ai/) has an LLM break a long response into claims, query external tools for evidence, and judge each claim. The approach covers text, code and math. [Self-Alignment with Instruction Backtranslation](https://md.research.elamur.ai/free/en/papers/li-2023-self-alignment-instruction-backtranslation/) borrows a trick from translation by having a model write the instructions that existing web text could answer. The resulting pairs are filtered and used for instruction tuning. An earlier 2019 paper dealt with word-order divergence in [low-resource](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/). The papers here carry bylines from [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) (2017–2025) and [Meta](https://md.research.elamur.ai/free/en/companies/meta/) (2021–2023). Frequent co-authors include [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/), [Luke Zettlemoyer](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/), Junxian He and Marjan Ghazvininejad. Chunting Zhou has 6 papers in our library, in 2019–2023, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/); often with [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/), [Luke Zettlemoyer](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/), [Junxian He](https://md.research.elamur.ai/free/en/authors/junxian-he/). 6 papers in our library · 2019–2023 [OpenAlex](https://openalex.org/A5110252779) · [**h-index 18**](https://openalex.org/authors/A5110252779) · [48 works](https://openalex.org/works?filter=author.id:A5110252779) · [1,875 citations](https://openalex.org/works?filter=author.id:A5110252779&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 6 works in our library](https://md.research.elamur.ai/free/en/authors/chunting-zhou/#papers) · [🔗 1,099 citations in our library](https://md.research.elamur.ai/free/en/authors/chunting-zhou/cited-by/) · [4 more in our library without a page yet](#also) · [⭐ Paper Star rank #1578](https://md.research.elamur.ai/free/en/paper-stars/page/16/#star-1578) 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=Chunting+Zhou) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Chunting+Zhou) · [dblp](https://dblp.org/search?q=Chunting+Zhou) · [ACL Anthology](https://aclanthology.org/search/?q=Chunting+Zhou) ## Affiliations [🎓**Wenzhou Medical University** Wenzhou · China 2024–2026 · 4 papers*current*](https://ror.org/00rd5t069) · [🎓**Carnegie Mellon University** Pittsburgh · United States 2017–2025 · 16 papers](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🏢**Meta** Menlo Park · United States 2021–2023 · 6 papers](https://md.research.elamur.ai/free/en/companies/meta/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed. ## Topics [Machine translation (2)](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Low-resource languages (1)](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) ## Works by year ### 2020s [**2023** 3 papers](https://md.research.elamur.ai/free/en/authors/chunting-zhou/year/2023/) · [**2021** 2 papers](https://md.research.elamur.ai/free/en/authors/chunting-zhou/year/2021/) ### 2010s [**2019** 1 paper](https://md.research.elamur.ai/free/en/papers/zhou-2019-handling-syntactic-divergence-low-resource/) ## Papers The most cited first (OpenAlex and our library). 1. **[Towards a Unified View of Parameter-Efficient Transfer Learning](https://md.research.elamur.ai/free/en/papers/he-2021-towards-unified-view-parameter-efficient/)** *(2021 · 604 citations)* Adapting large pretrained language models by updating every weight requires a separate full copy of the model for each task, which becomes costly as models grow. 2. **[In-context Examples Selection for Machine Translation](https://md.research.elamur.ai/free/en/papers/agrawal-2023-context-examples-selection-machine-translation/)** *(2023 · 241 citations)* The paper asks how the choice and ordering of in-context demonstrations shape the output of a large generative model when it is used for machine translation. 3. **[Detecting Hallucinated Content in Conditional Neural Sequence Generation](https://md.research.elamur.ai/free/en/papers/zhou-2021-detecting-hallucinated-content-conditional-neural/)** *(2021 · 229 citations)* Neural generators for translation and summarization can produce fluent output that contains material the input does not support. 4. **[FacTool: Factuality Detection in Generative AI — A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios](https://md.research.elamur.ai/free/en/papers/chern-2023-factool-factuality-detection-generative-ai/)** *(2023 · 158 citations)* Large language models such as ChatGPT write fluent long-form answers that may contain factual errors. Classic fact-checking setups rarely fit this case. They usually assume that the claim to check, or the evidence for it, is already given. LLM outputs instead come without either, and they are long, with no clear unit… 5. **[Self-Alignment with Instruction Backtranslation](https://md.research.elamur.ai/free/en/papers/li-2023-self-alignment-instruction-backtranslation/)** *(2023 · 131 citations)* Instruction-tuning LLMs usually depends on costly human-written demonstrations or on outputs distilled from stronger proprietary models, and high-quality annotation is hard to scale. 6. **[Handling Syntactic Divergence in Low-resource Machine Translation](https://md.research.elamur.ai/free/en/papers/zhou-2019-handling-syntactic-divergence-low-resource/)** *(2019 · 33 citations)* Back-translation needs a working reverse system, so it fails when parallel data is tiny and the languages differ in word order. ## Also in our library 4 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 12 of 19 co-authors with a page, the most papers together first. - [Graham Neubig](https://md.research.elamur.ai/free/en/authors/graham-neubig/) ×4 - [Luke Zettlemoyer](https://md.research.elamur.ai/free/en/authors/luke-zettlemoyer/) ×3 - [Junxian He](https://md.research.elamur.ai/free/en/authors/junxian-he/) ×2 - [Marjan Ghazvininejad](https://md.research.elamur.ai/free/en/authors/marjan-ghazvininejad/) ×2 - [Mike Lewis](https://md.research.elamur.ai/free/en/authors/mike-lewis/) ×2 - [Xuezhe Ma](https://md.research.elamur.ai/free/en/authors/xuezhe-ma/) ×2 - [Francisco Guzmán](https://md.research.elamur.ai/free/en/authors/francisco-guzman/) - [Jason Weston](https://md.research.elamur.ai/free/en/authors/jason-weston/) - [Jiatao Gu](https://md.research.elamur.ai/free/en/authors/jiatao-gu/) - [Junjie Hu](https://md.research.elamur.ai/free/en/authors/junjie-hu/) - [Mona Diab](https://md.research.elamur.ai/free/en/authors/mona-diab/) - [Omer Levy](https://md.research.elamur.ai/free/en/authors/omer-levy/) ## Cited by Papers of our library cite their works 1,099 times (of the 140,884 papers whose bibliographies we read); [81 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/chunting-zhou/cited-by/).