--- title: "Pinjia He — author profile and papers — Elamur Research" description: "Pinjia He, Chinese University of Hong Kong: 4 papers on Elamur Research (2023–2026), h-index 28 — affiliations, topics, co-authors and…" canonical: "https://research.elamur.ai/free/en/authors/pinjia-he/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/pinjia-he/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Pinjia He # Pinjia He Pinjia He has 4 papers in our library, in 2023–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Bias, fairness & safety](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/), [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/); often with [Youliang Yuan](https://md.research.elamur.ai/free/en/authors/youliang-yuan/), [Jen-tse Huang](https://md.research.elamur.ai/free/en/authors/jen-tse-huang/), [Wenxuan Wang](https://md.research.elamur.ai/free/en/authors/wenxuan-wang/). 4 papers in our library · 2023–2026 [OpenAlex](https://openalex.org/A5101941950) · [ORCID](https://orcid.org/0000-0003-3377-8129) · [Wikidata](https://www.wikidata.org/wiki/Q130810134) · [**h-index 28**](https://openalex.org/authors/A5101941950) · [115 works](https://openalex.org/works?filter=author.id:A5101941950) · [5,604 citations](https://openalex.org/works?filter=author.id:A5101941950&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 4 works in our library](https://md.research.elamur.ai/free/en/authors/pinjia-he/#papers) · [🔗 Cited 173 times in our library](https://md.research.elamur.ai/free/en/authors/pinjia-he/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #5730](https://md.research.elamur.ai/free/en/paper-stars/page/58/#star-5730) 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=Pinjia+He) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Pinjia+He) · [dblp](https://dblp.org/search?q=Pinjia+He) · [ACL Anthology](https://aclanthology.org/search/?q=Pinjia+He) ## Affiliations [🎓**Chinese University of Hong Kong, Shenzhen** Shenzhen · China 2014–2026 · 81 papersEmployment since 2021 · Assistant Professor, School of Data Science*current*](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong-shenzhen/) · [🎓**Chinese University of Hong Kong** Hong Kong · China 2014–2026 · 26 papers*current*](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong/) · [🎓**ETH Zurich** Zurich · Switzerland 2018–2021 · 11 papersEmployment 2018–2021 · Postdoc, Computer Science](https://md.research.elamur.ai/free/en/universities/eth-zurich/) · [🎓**Shenzhen Research Institute of Big Data** Shenzhen · China 2023–2025 · 8 papers](https://md.research.elamur.ai/free/en/universities/shenzhen-research-institute-of-big-data/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 8 The field of science this work belongs to (OpenAlex fields).[Computer Science · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Safety Research · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 2 works](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · [Computer Vision and Pattern Recognition · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) 🧭 Topics 3 Research subjects and languages the work is about.[Language models & pretraining · 4 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Bias, fairness & safety · 2 works](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Vision & language · 1 work](https://md.research.elamur.ai/free/en/topics/multimodal/) ## Works by year ### 2020s [**2026** 1 paper](https://md.research.elamur.ai/free/en/authors/pinjia-he/year/2026/) · [**2025** 2 papers](https://md.research.elamur.ai/free/en/authors/pinjia-he/year/2025/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/pinjia-he/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://md.research.elamur.ai/free/en/papers/yuan-2023-gpt-4-too-smart-safe/)** *(2023 · 168 citations)* The paper examines whether safety alignment in large language models, which is trained mostly on natural-language data, still holds when users communicate through encoded text. 2. **[Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training](https://md.research.elamur.ai/free/en/papers/yuan-2025-refuse-whenever-you-feel-unsafe/)** *(2025 · 19 citations)* Safety-tuning data for LLMs usually places refusal phrases ("Sorry", "I cannot") at the very start of the reply. 3. **[Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs](https://md.research.elamur.ai/free/en/papers/liu-2025-insight-over-sight-exploring-vision/)** *(2025 · 6 citations)* The paper investigates how multimodal LLMs behave when an image contradicts everyday commonsense they absorbed during training. 4. **[SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs](https://md.research.elamur.ai/free/en/papers/zhao-2026-shape-unifying-safety-helpfulness-pedagogy/)** *(2026 · 2 citations)* The paper looks at a weakness of LLM tutors that the authors call "pedagogical jailbreaks." In these attacks, students write prompts designed to extract final solutions when the tutor should be guiding them step by step. ## All works 5 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them. 1. [**GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher arXiv:2308.06463**Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, et al.*2023 · 168 citations*](https://md.research.elamur.ai/free/en/papers/yuan-2023-gpt-4-too-smart-safe/) 2. **[Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training](https://md.research.elamur.ai/free/en/papers/yuan-2025-refuse-whenever-you-feel-unsafe/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Youliang Yuan, Wenxiang Jiao, Wenxuan Wang, et al.*2025 · 19 citations* 3. **[Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs](https://md.research.elamur.ai/free/en/papers/liu-2025-insight-over-sight-exploring-vision/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Xiaoyuan Liu, Wenxuan Wang, Youliang Yuan, et al.*2025 · 6 citations* 4. **[SHAPE: Unifying Safety, Helpfulness and Pedagogy for Educational LLMs](https://md.research.elamur.ai/free/en/papers/zhao-2026-shape-unifying-safety-helpfulness-pedagogy/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Sihang Zhao, Kangrui Yu, Youliang Yuan, et al.*2026 · 2 citations* 5. **[Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards ↗](https://aclanthology.org/2026.acl-long.844/) Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · no summary yet**Youliang Yuan et al.*2026* ## Co-authors here 10 co-authors with a page, the most papers together first. - [Youliang Yuan](https://md.research.elamur.ai/free/en/authors/youliang-yuan/) ×4 - [Jen-tse Huang](https://md.research.elamur.ai/free/en/authors/jen-tse-huang/) ×3 - [Wenxuan Wang](https://md.research.elamur.ai/free/en/authors/wenxuan-wang/) ×3 - [Zhaopeng Tu](https://md.research.elamur.ai/free/en/authors/zhaopeng-tu/) ×3 - [Wenxiang Jiao](https://md.research.elamur.ai/free/en/authors/wenxiang-jiao/) ×2 - [Jiahao Xu](https://md.research.elamur.ai/free/en/authors/jiahao-xu/) - [Qiuzhi Liu](https://md.research.elamur.ai/free/en/authors/qiuzhi-liu/) - [Shuming Shi](https://md.research.elamur.ai/free/en/authors/shuming-shi/) - [Tian Liang](https://md.research.elamur.ai/free/en/authors/tian-liang/) - [Xiaoyuan Liu](https://md.research.elamur.ai/free/en/authors/xiaoyuan-liu/) ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×4: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/), [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/) ×2 ## Cited by Papers of our library cite their works 173 times (of the 149,439 papers whose bibliographies we read); [54 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/pinjia-he/cited-by/). Updated 31 October 2026