--- title: "Zhiyu Xue — author profile and papers · Bias, fairness & safety" description: "Zhiyu Xue, University of California, Santa Barbara: 3 papers on Elamur Research (2026), h-index 2 — affiliations, topics, co-authors and who…" canonical: "https://research.elamur.ai/free/en/authors/zhiyu-xue/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/zhiyu-xue/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Zhiyu Xue # Zhiyu Xue Zhiyu Xue has 3 papers in our library, in 2026, most of them on [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 [Ramtin Pedarsani](https://md.research.elamur.ai/free/en/authors/ramtin-pedarsani/), [Reza Abbasi-Asl](https://md.research.elamur.ai/free/en/authors/reza-abbasi-asl/). 3 papers in our library · 2026 [OpenAlex](https://openalex.org/A5040852802) · [ORCID](https://orcid.org/0009-0009-1389-0499) · [**h-index 2**](https://openalex.org/authors/A5040852802) · [19 works](https://openalex.org/works?filter=author.id:A5040852802) · [11 citations](https://openalex.org/works?filter=author.id:A5040852802&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 3 works in our library](https://md.research.elamur.ai/free/en/authors/zhiyu-xue/#papers) · [🔗 Cited 3 times in our library](https://md.research.elamur.ai/free/en/authors/zhiyu-xue/cited-by/) · [2 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #12819](https://md.research.elamur.ai/free/en/paper-stars/page/129/#star-12819) 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=Zhiyu+Xue) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Zhiyu+Xue) · [dblp](https://dblp.org/search?q=Zhiyu+Xue) · [ACL Anthology](https://aclanthology.org/search/?q=Zhiyu+Xue) ## Affiliations [🎓**University of California, Santa Barbara** Santa Barbara · United States 2023–2026 · 14 papersEmployment since 2024 · Research Assistant, ECE*current*](https://md.research.elamur.ai/free/en/universities/university-of-california-santa-barbara/) · [🎓**Michigan State University** East Lansing · United States 2022–2023 · 3 papers](https://md.research.elamur.ai/free/en/universities/michigan-state-university/) 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 7 The field of science this work belongs to (OpenAlex fields).[Computer Science · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 3 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Vision and Pattern Recognition · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Health Informatics · 1 work](https://md.research.elamur.ai/free/en/shelves/medicine/health-informatics/) · [Medicine · 1 work](https://md.research.elamur.ai/free/en/shelves/medicine/) · [Safety Research · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/) 🧭 Topics 2 Research subjects and languages the work is about.[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** 3 papers](https://md.research.elamur.ai/free/en/authors/zhiyu-xue/year/2026/) ## Papers The most cited first (OpenAlex and our library). 1. **[Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations](https://md.research.elamur.ai/free/en/papers/xue-2026-enhancing-safety-medical-vision-language/)** *(2026 · 1 citation)* Generative medical vision-language models (Med-VLMs) can be pushed into answering malicious requests, such as using a scan to commit fraud. 2. **[Benchmarking and Mitigating the Impact of Noisy User Prompts in Medical VLMs via Cross-Modal Reflection](https://md.research.elamur.ai/free/en/papers/xue-2026-benchmarking-mitigating-impact-noisy-user/)** *(2026)* Medical vision-language models (Med-VLMs) are often given user-supplied clinical hints, but it was unclear how they react when those hints are wrong. 3. **[Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment](https://md.research.elamur.ai/free/en/papers/xue-2026-deactivating-refusal-triggers-understanding-mitigating/)** *(2026)* Safety-aligned LLMs often refuse harmless requests, a failure known as overrefusal. This paper asks why safety fine-tuning causes it. The authors argue that harmful training queries contain non-harmful parts, such as ordinary events ("create a video") or polite help-seeking phrases ("Can you help me"). During… ## All works 5 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them. 1. **[Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models ↗](https://arxiv.org/abs/2603.18523) arXiv (Cornell University) · no summary yet**Liwei Che et al.*2026 · 2 citations* 2. **[Enhancing the Safety of Medical Vision-Language Models by Synthetic Demonstrations](https://md.research.elamur.ai/free/en/papers/xue-2026-enhancing-safety-medical-vision-language/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Zhiyu Xue, Reza Abbasi-Asl, Ramtin Pedarsani*2026 · 1 citation* 3. **[Benchmarking and Mitigating the Impact of Noisy User Prompts in Medical VLMs via Cross-Modal Reflection](https://md.research.elamur.ai/free/en/papers/xue-2026-benchmarking-mitigating-impact-noisy-user/) [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/)**Zhiyu Xue, Reza Abbasi-Asl, Ramtin Pedarsani*2026* 4. **[Deactivating Refusal Triggers: Understanding and Mitigating Overrefusal in Safety Alignment](https://md.research.elamur.ai/free/en/papers/xue-2026-deactivating-refusal-triggers-understanding-mitigating/) [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/)**Zhiyu Xue, Zimo Qi, Guangliang Liu, et al.*2026* 5. **[Learning from Primitive: Probing Visual Reasoning of LVLMs via Counting ↗](https://doi.org/10.1007/978-3-032-37023-5_37) Lecture notes in computer science · no summary yet**Liwei Che et al.*2026* ## Co-authors here 2 co-authors with a page, the most papers together first. - [Ramtin Pedarsani](https://md.research.elamur.ai/free/en/authors/ramtin-pedarsani/) ×3 - [Reza Abbasi-Asl](https://md.research.elamur.ai/free/en/authors/reza-abbasi-asl/) ×2 ## Venues Where their works here were published, the most works first, with the editions of those that have a page. - [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/) ×2: [EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/) ×2 - [Workshop on Trustworthy NLP](https://md.research.elamur.ai/free/en/venues/trustnlp/): [Workshop on Trustworthy NLP 2026](https://md.research.elamur.ai/free/en/venues/trustnlp/2026/) - Lecture notes in computer science ## Cited by Papers of our library cite their works 3 times (of the 149,439 papers whose bibliographies we read); [2 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/zhiyu-xue/cited-by/). Updated 2 November 2026