Yujia Zheng
Yujia Zheng has 2 papers in our library, in 2026, most of them on Language models & pretraining, Interpretability; often with Aashiq Muhamed, Jingyu Lu, Kun Zhang.
OpenAlex · ORCID · h-index 7 · 24 works · 188 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 1 time in our library · ⭐ Paper Stars ranking: #13226
Affiliations
Fields, topics and concepts
📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksArts and Humanities · 2 worksComputer Science · 2 worksLanguage and Linguistics · 2 works
🧭 Topics 2Research subjects and languages the work is about.Interpretability · 1 workLanguage models & pretraining · 1 work
Works by year
2020s
Papers
- Mechanistic Interpretability Should Prioritize Feature Consistency in Sparse Autoencoders (2026 · 1 citation)
Sparse autoencoders (SAEs) are a popular way to break LLM activations into sparse, human-readable features. - Are All Prompt Components Value-Neutral? Understanding the Heterogeneous Adversarial Robustness of Dissected Prompt in LLMs (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
- Aashiq Muhamed
- Jingyu Lu
- Kun Zhang
- Lingjing Kong
- Mona Diab
- Tianhao Li
- Virginia Smith
- Xiangchen Song
- Yuyao Ge
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- Conference of the European Chapter of the Association for Computational Linguistics (EACL): EACL 2026
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/yujia-zheng/