--- title: "Yujia Zheng — author profile and papers — Elamur Research" description: "Yujia Zheng: 2 papers on Elamur Research (2026), h-index 7 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/yujia-zheng/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yujia-zheng/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Yujia Zheng # Yujia Zheng Yujia Zheng has 2 papers in our library, in 2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/); often with [Aashiq Muhamed](https://md.research.elamur.ai/free/en/authors/aashiq-muhamed/), [Jingyu Lu](https://md.research.elamur.ai/free/en/authors/jingyu-lu/), [Kun Zhang](https://md.research.elamur.ai/free/en/authors/kun-zhang/). 2 papers in our library · 2026 [OpenAlex](https://openalex.org/A5035967581) · [ORCID](https://orcid.org/0009-0006-0795-4204) · [**h-index 7**](https://openalex.org/authors/A5035967581) · [24 works](https://openalex.org/works?filter=author.id:A5035967581) · [188 citations](https://openalex.org/works?filter=author.id:A5035967581&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 2 works in our library](https://md.research.elamur.ai/free/en/authors/yujia-zheng/#papers) · 🔗 Cited 1 time in our library · [⭐ Paper Stars ranking: #13226](https://md.research.elamur.ai/free/en/paper-stars/page/133/#star-13226) 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=Yujia+Zheng) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Yujia+Zheng) · [dblp](https://dblp.org/search?q=Yujia+Zheng) · [ACL Anthology](https://aclanthology.org/search/?q=Yujia+Zheng) ## Affiliations [🎓**North China University of Technology** Beijing · China 2023–2025 · 15 papers](https://md.research.elamur.ai/free/en/universities/north-china-university-of-technology/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 6 more institutions on single bylines are not listed. ## Fields, topics and concepts Of its works in our library, with the number of works on each. 📚 Shelves 4 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Computer Science · 2 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Language and Linguistics · 2 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) 🧭 Topics 2 Research subjects and languages the work is about.[Interpretability · 1 work](https://md.research.elamur.ai/free/en/topics/interpretability/) · [Language models & pretraining · 1 work](https://md.research.elamur.ai/free/en/topics/language-models/) ## Works by year ### 2020s [**2026** 2 papers](https://md.research.elamur.ai/free/en/authors/yujia-zheng/year/2026/) ## Papers The most cited first (OpenAlex and our library). 1. **[Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders](https://md.research.elamur.ai/free/en/papers/song-2026-mechanistic-interpretability-should-prioritize-feature/)** *(2026 · 1 citation)* Sparse autoencoders (SAEs) are a popular way to break LLM activations into sparse, human-readable features. 2. **[Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs](https://md.research.elamur.ai/free/en/papers/zheng-2026-are-all-prompt-components-value/)** *(2026)* Most work on adversarial prompting treats a prompt as one undivided string. This paper argues instead that prompts are built from functional parts, and that these parts differ in how easily an attack can exploit them. ## Co-authors here 9 co-authors with a page, the most papers together first. - [Aashiq Muhamed](https://md.research.elamur.ai/free/en/authors/aashiq-muhamed/) - [Jingyu Lu](https://md.research.elamur.ai/free/en/authors/jingyu-lu/) - [Kun Zhang](https://md.research.elamur.ai/free/en/authors/kun-zhang/) - [Lingjing Kong](https://md.research.elamur.ai/free/en/authors/lingjing-kong/) - [Mona Diab](https://md.research.elamur.ai/free/en/authors/mona-diab/) - [Tianhao Li](https://md.research.elamur.ai/free/en/authors/tianhao-li/) - [Virginia Smith](https://md.research.elamur.ai/free/en/authors/virginia-smith/) - [Xiangchen Song](https://md.research.elamur.ai/free/en/authors/xiangchen-song/) - [Yuyao Ge](https://md.research.elamur.ai/free/en/authors/yuyao-ge/) ## 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/): [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) - [Conference of the European Chapter of the Association for Computational Linguistics (EACL)](https://md.research.elamur.ai/free/en/venues/eacl/): [EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/) ## Cited by Papers of our library cite their works 1 time (of the 149,439 papers whose bibliographies we read). Updated 2 November 2026