About Me

Hello, I’m Yunzhi Yao (姚云志), a fourth-year Ph.D. student (expected to graduate in 2026.06) in the College of Computer Science and Technology at Zhejiang University, supervised by Prof. Huajun Chen and Prof. Ningyu Zhang. Now, I am a visiting research scholar at UCLA, working with Prof. Nanyun Peng. I was also fortunate to be advised by Shaohan Huang in MSRA. I earned my Bachelor’s degree in Software Engineering and Dual Degree in Finance from Shandong University in 2021.

Research Interest

My primary research interests lie in machine learning for natural language processing, with a particular focus on the knowledge mechanisms underpinning large language models (LLMs). I’m open to different research fileds and currently, I am actively exploring the following topics:

• Knowledge Mechanisms and Editing: I am passionate about investigating how LLMs acquire, store, and utilize knowledge for reasoning. My goal is to develop concise and precise methods for model editing that enhance these capabilities.
• Model Merging: I am also dedicated to exploring the connections between models with diverse architectures and modalities. I believe that these models have the potential to communicate and integrate information in ways that transcend traditional text-based interactions.

Btw, I’m interested in Astrology. If you are interested in talking about research and life with me, please feel free to reach out.

Selected Projects

• CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners.

  Yunzhi Yao, Jizhan Fang, Jia-Chen Gu, Ningyu Zhang, Shumin Deng, Huajun Chen, Nanyun Peng.

  Oral@NENLP 2025

  PDF Code

• Knowledge Circuits in Pretrained Transformers.

  Yunzhi Yao, Ningyu Zhang, Zekun Xi, Mengru Wang, Ziwen Xu, Shumin Deng, Huajun Chen.

  In Proceedings of the 38th Neural Information Processing Systems (Neurips 2024)

  PDF Code Video

• Editing Large Language Models: Problems, Methods, and Opportunities.

  Yunzhi Yao, Peng Wang, Bozhong Tian, Siyuan Cheng, Zhoubo Li, Shumin Deng, Huajun Chen, Ningyu Zhang.

  In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)

  PDF Code Video

• Knowledge Rumination for Pre-trained Language Models.

  Yunzhi Yao, Peng Wang, Shengyu Mao, Chuanqi Tan, Fei Huang, Huajun Chen, Ningyu Zhang.

  In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)

  PDF Code

• Schema-aware reference as prompt improves data-efficient knowledge graph construction.

  Yunzhi Yao, Shengyu Mao, Ningyu Zhang, Xiang Chen, Shumin Deng, Xi Chen, Huajun Chen.

  In Proceedings of the 46th International ACM SIGIR Conference (SIGIR 2023)

  PDF Code

• Kformer: Knowledge injection in transformer feed-forward layers.

  Yunzhi Yao, Shaohan Huang, Li Dong, Furu Wei, Huajun Chen, Ningyu Zhang.

  In Proceedings of the 11th Natural Language Processing and Chinese Computing (NLPCC 2022)

  PDF Code

• Adapt-and-distill: Developing small, fast and effective pretrained language models for domains.

  Yunzhi Yao, Shaohan Huang, Wenhui Wang, Li Dong, Furu Wei.

  In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (ACL 2021)

  PDF Code

Honor and Awards

• Best Paper Award, Workshop LLM+KG@VLDB2024
• National Scholarship (2024), Zhejiang University
• Star of Tomorrow (2021), Microsoft Research Asia
• Excellent Graduate (2021), Shandong University
• National Scholarship (2018), Shandong University

Professional Services

• Area Chair: ACL ARR
• Reviewer: ACL ARR, NeurIPS, ICML, ICLR, TASLP, COLM, ACM MM, AISTATS, NLPCC
• Volunteer: AI TIME

Tutorials

• Knowledge Editing for Large Language Models @ IJCAI 2024.

  Ningyu Zhang, Jia-Chen Gu, Yunzhi Yao, Mengru Wang, Xiang Chen, Shumin Deng.

  Link PDF

• Knowledge Editing for Large Language Models @ COLING 2024.

  Ningyu Zhang, Yunzhi Yao, Shumin Deng.

  Link PDF

• Knowledge Editing for Large Language Models @ AACL 2023.

  Ningyu Zhang, Yunzhi Yao, Shumin Deng.

  Link PDF