--- title: "Jingbo Shang — author profile and papers" description: "Jingbo Shang, University of Notre Dame: 3 papers on Elamur Research (2017–2023), h-index 29 — affiliations, topics, co-authors and who cites them in our…" canonical: "https://research.elamur.ai/free/en/authors/jingbo-shang/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/jingbo-shang/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Jingbo Shang # Jingbo Shang Jingbo Shang's papers here address natural language processing when labeled examples are scarce. One recurring question is how to train neural sequence taggers, such as part-of-speech taggers, chunkers and named entity recognizers, without large hand-annotated corpora. Another is how detection systems cope when real inputs differ from the text they were built on. The methods include language-model objectives used as auxiliary signals, distant supervision from dictionaries and mined phrases, and purpose-built benchmarks for evaluation. The most cited of these works is [Empower Sequence Labeling with Task-Aware Neural Language Model](https://md.research.elamur.ai/free/en/papers/liu-2017-empower-sequence-labeling-task-aware/) (2017). It introduced LM-LSTM-CRF, in which a character-level language model is learned alongside the sequence labeler, both drawing on the very sentences already annotated for the task. The tagger thus gains extra signal without any additional annotation or outside corpus. A year later, [Learning Named Entity Tagger using Domain-Specific Dictionary](https://md.research.elamur.ai/free/en/papers/shang-2018-learning-named-entity-tagger-domain/) (2018) built entity taggers for specialized domains from nothing more than a dictionary and unlabeled text. Training labels come from exact string matches. Because a dictionary never covers every entity, quality phrases extracted from the corpus are also treated as entities, given a type marked as unknown. The newest paper listed turns from tagging to safety. [ToxicChat](https://md.research.elamur.ai/free/en/papers/lin-2023-toxicchat-unveiling-hidden-challenges-toxicity/) (2023) argues that toxicity detectors built from social media posts fit poorly with how people actually address chatbots. Users often frame harmful requests as questions or instructions, or hide them in jailbreaking prompts that look harmless. The benchmark collects 10,166 opening user queries from the public Vicuna demo, each annotated for toxicity and for jailbreaking attempts. It sits under the topic [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/), alongside the earlier work on [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/). Shang has been at the [University of California San Diego](https://md.research.elamur.ai/free/en/universities/university-of-california-san-diego/) since 2020. Frequent co-authors on the papers here include [Jiawei Han](https://md.research.elamur.ai/free/en/authors/jiawei-han/), [Liyuan Liu](https://md.research.elamur.ai/free/en/authors/liyuan-liu/) and [Xiang Ren](https://md.research.elamur.ai/free/en/authors/xiang-ren/). Jingbo Shang has 3 papers in our library, in 2017–2023, most of them on [Named entity recognition](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/), [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/); often with [Jiawei Han](https://md.research.elamur.ai/free/en/authors/jiawei-han/), [Liyuan Liu](https://md.research.elamur.ai/free/en/authors/liyuan-liu/), [Xiang Ren](https://md.research.elamur.ai/free/en/authors/xiang-ren/). 3 papers in our library · 2017–2023 [OpenAlex](https://openalex.org/A5039500313) · [ORCID](https://orcid.org/0000-0002-7249-4404) · [Wikidata](https://www.wikidata.org/wiki/Q124821052) · [**h-index 29**](https://openalex.org/authors/A5039500313) · [255 works](https://openalex.org/works?filter=author.id:A5039500313) · [4,329 citations](https://openalex.org/works?filter=author.id:A5039500313&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/jingbo-shang/#papers) · [🔗 516 citations in our library](https://md.research.elamur.ai/free/en/authors/jingbo-shang/cited-by/) · [11 more in our library without a page yet](#also) · [⭐ Paper Star rank #2209](https://md.research.elamur.ai/free/en/paper-stars/page/23/#star-2209) 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=Jingbo+Shang) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Jingbo+Shang) · [dblp](https://dblp.org/search?q=Jingbo+Shang) · [ACL Anthology](https://aclanthology.org/search/?q=Jingbo+Shang) ## Affiliations [🎓**University of California San Diego** San Diego · United States 2020–2026 · 151 papers*current*](https://md.research.elamur.ai/free/en/universities/university-of-california-san-diego/) · [🏢**Amazon** Seattle · United States 2024–2026 · 4 papers*current*](https://md.research.elamur.ai/free/en/companies/amazon/) · [🎓**University of San Diego** San Diego · United States 2026 · 2 papers*current*](https://ror.org/03jbbze48) · [🏢**Adobe Systems** San Jose · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/companies/adobe-systems/) · [🎓**Georgia Institute of Technology** Atlanta · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/georgia-institute-of-technology/) · [🤝**La Jolla Bioengineering Institute** San Diego · United States 2026 · 1 paper*current*](https://ror.org/03sgbh608) · [🎓**University of Notre Dame** Notre Dame · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/universities/university-of-notre-dame/) · [🎓**University of Illinois Urbana-Champaign** Urbana · United States 2014–2022 · 46 papers](https://md.research.elamur.ai/free/en/universities/university-of-illinois-urbana-champaign/) · [🏢**Google** Mountain View · United States 2022–2023 · 4 papers](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**Shanghai Jiao Tong University** Shanghai · China 2014–2015 · 4 papers](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 9 more institutions on single bylines are not listed. ## Topics [Named entity recognition (1)](https://md.research.elamur.ai/free/en/topics/named-entity-recognition/) · [Part-of-speech tagging (1)](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) · [Language models & pretraining (1)](https://md.research.elamur.ai/free/en/topics/language-models/) · [Bias, fairness & safety (1)](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) ## Works by year ### 2020s [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/lin-2023-toxicchat-unveiling-hidden-challenges-toxicity/) ### 2010s [**2018** 1 paper](https://md.research.elamur.ai/free/en/papers/shang-2018-learning-named-entity-tagger-domain/) · [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/liu-2017-empower-sequence-labeling-task-aware/) ## Papers The most cited first (OpenAlex and our library). 1. **[Empower Sequence Labeling with Task-Aware Neural Language Model](https://md.research.elamur.ai/free/en/papers/liu-2017-empower-sequence-labeling-task-aware/)** *(2017 · 419 citations)* Neural sequence labelers for POS tagging, chunking and NER have many parameters, but annotated corpora are usually small. 2. **[Learning Named Entity Tagger using Domain-Specific Dictionary](https://md.research.elamur.ai/free/en/papers/shang-2018-learning-named-entity-tagger-domain/)** *(2018 · 301 citations)* Neural NER models no longer need handcrafted features, but they still need large amounts of manually labeled text. 3. **[ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation](https://md.research.elamur.ai/free/en/papers/lin-2023-toxicchat-unveiling-hidden-challenges-toxicity/)** *(2023 · 127 citations)* Most toxicity detectors are trained on social media text. Users of LLM chatbots behave differently: they phrase harmful intent as questions or instructions, and they sometimes use "jailbreaking" prompts that look benign but aim to make the model bypass its policies. To study this gap, the authors built ToxicChat, the… ## Also in our library 11 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 7 co-authors with a page, the most papers together first. - [Jiawei Han](https://md.research.elamur.ai/free/en/authors/jiawei-han/) ×2 - [Liyuan Liu](https://md.research.elamur.ai/free/en/authors/liyuan-liu/) ×2 - [Xiang Ren](https://md.research.elamur.ai/free/en/authors/xiang-ren/) ×2 - [Frank F. Xu](https://md.research.elamur.ai/free/en/authors/frank-f-xu/) - [Jian Peng](https://md.research.elamur.ai/free/en/authors/jian-peng/) - [Zi Lin](https://md.research.elamur.ai/free/en/authors/zi-lin/) - [Zihan Wang](https://md.research.elamur.ai/free/en/authors/zihan-wang/) ## Cited by Papers of our library cite their works 516 times (of the 140,884 papers whose bibliographies we read); [25 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/jingbo-shang/cited-by/).