Yuji Zhang (张雨季) Postdoc University of Illinois at Urbana-Champaign, Email: yujiz@illinois.edu   or                yuji.celestine (at) gmail.com Google Scholar Twitter

I am a postdoc researcher in the University of Illinois at Urbana-Champaign (UIUC). I am fortunately supervised by Professor Heng Ji in BLENDER LAB@UIUC.

Research

I have broad interests in Natural Language Processing (NLP), theoretical interpretation of large language models (LLMs), and trustworthy LLMs. Especially, I focus on the following directions:

• how to effectively and efficiently acquire real-world knowledge to equip and update large language models in the temporally evolving world.
• I am recently focusing on interpreting why large language models hallucinate.

Publications

(see full list in Google Scholar)

2020 - Present

• Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models

  Yuji Zhang, Sha Li, Jiateng Liu, Pengfei Yu, Yi R. Fung, Jing Li, Manling Li, Heng Ji.
  Arxiv preprint
  [Arxiv]

• EVEDIT: Event-based Knowledge Editing with Deductive Editing Boundaries

  Jiateng Liu*, Pengfei Yu*, Yuji Zhang, Sha Li, Zixuan Zhang, Heng Ji.
  Arxiv preprint.
  [Arxiv]

• VIBE: Topic-Driven Temporal Adaptation for Twitter Classification

  Yuji Zhang, Jing Li, Wenjie Li.
  Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2023.
  [EMNLP 2023]

• Towards Fair Financial Services for All: A Temporal GNN Approach for Individual Fairness on Transaction Networks

  Zixing Song, Yuji Zhang, Irwin King.
  Proceedings of the 32nd ACM International Conference on Information and Knowledge Management.
  [CIKM '23]

• Time Will Change Things: An Empirical Study on Dynamic Language Understanding in Social Media Classification

  Yuji Zhang, Jing Li.
  ArXiv preprint.
  [arXiv]

• # HowYouTagTweets: Learning User Hashtagging Preferences via Personalized Topic Attention

  Yuji Zhang, Yubo Zhang, Chunpu Xu, Jing Li, Ziyan Jiang, Baolin Peng.
  Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 2021.
  [EMNLP 2021]

• Engage the Public: Poll Question Generation for Social Media Posts

  Zexin Lu, Keyang Ding, Yuji Zhang, Jing Li, Baolin Peng, Lemao Liu.
  Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.
  [ACL 2021]

• Hashtags, emotions, and comments: a large-scale dataset to understand fine-grained social emotions to online topics

  Keyang Ding, Jing Li, Yuji Zhang.
  Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).
  [EMNLP 2020]

• Capacitivo: Contact-Based Object Recognition on Interactive Fabrics using Capacitive Sensing

  Te-Yen Wu, Lu Tan, Yuji Zhang, Teddy Seyed, Xing-Dong Yang.
  UIST '20: Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology.
  [UIST '20]

Honors

• Outstanding Student Leader of Southeast University 2017, 2018, 2019
• Second Prize in National Undergraduate Mathematical Contest in Modeling, 2018
• Skyworth Scholarship, 2018
• National Scholarship (Top 1%, the highest scholarship for undergraduates), 2017
• Merit Student of Jiangsu Province (Top 0.1%), 2016

Experiences

• 2020/01 - 2020/06: Research intern at Dartmouth College (Advisors: Prof. Xingdong Yang, Prof. Te-Yen Wu)
• 2023/12 - 2024/08: Visiting PhD student at UIUC (Advisor: Prof. Heng Ji)

Professional Activities

Teaching Assistant

• COMP 5511: Artificial Intelligence Concepts, Spring 2023, PolyU
• COMP 4141: Crowdfunding and e-Finance, Spring 2022, PolyU
• COMP 1433: Introduction to Data Analytics, Spring 2021, PolyU

Conference Reviewer

• ACL ARR (2023), KDD (2023), EMNLP (2023), EACL (2023), COLING (2023)

Misc.

• I enjoy reading and crafts. I have practiced taekwondo and piano for four years.

• In my free time, I love hiking, swimming, and exploring various cultural destinations.