Zihan Xue

PhD student · Northeastern University

xue.zih [at] northeastern [dot] edu · Google Scholar

I’m a first-year PhD student in Computer Science at Northeastern University, advised by Prof. Dakuo Wang in the HAI Lab.

I study how AI agents navigate human goals, preferences, and expectations, especially in settings where good behavior is hard to define or measure. I’m interested in how agents can account for individual preferences, how we can evaluate what they do, and how our expectations of them shift as they take on more autonomous roles.

Before my PhD, I studied Computer Science at UCLA, where I did research in Prof. Nanyun (Violet) Peng’s group. I also worked closely with Prof. Kuan-Hao Huang at Texas A&M.

Papers

1. TwinICL: Diagnosing Multimodal In-Context Learning through Paired Counterfactuals
   Zihan Xue, Po-Yi Lu, Serhii Honcharenko, Zih-Ching Chen, Hsuan-Tien Lin, Nanyun Peng, I-Hung Hsu, Kuan-Hao Huang
   arXiv preprint 2026paper
2. FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback
   Xueqing Wu, Zihan Xue, Da Yin, Shuyan Zhou, Kai-Wei Chang, Nanyun Peng, Yeming Wen
   COLM 2026paper
3. LegalDiscourse: Interpreting When Laws Apply and To Whom
   Alexander Spangher, Zihan Xue, Te-Lin Wu, Mark Hansen, Jonathan May
   NAACL 2024paper
4. Argument-Aware Approach To Event Linking
   I-Hung Hsu*, Zihan Xue*, Nilay Pochhi, Sahil Bansal, Premkumar Natarajan, Jayanth Srinivasa, Nanyun Peng
   Findings of ACL 2024paper

* equal contribution