Image

Chi Han 韩迟

Chi Han is a PhD candidate at UIUC CS, advised by Prof. Heng Ji. Previously, he obtained his Bachelor's degree from YaoClass, Tsinghua University. Expected graduation in June 2026.

[Twitter]; [Google Scholar]; [GitHub]; [Curriculum Vitae];
My Research

My long-term research goal is to develop a principled science for analyzing and reprogramming large language models (LLMs) to fundamentally bridge their gaps across domains and scientific disciplines. I believe that there exist hidden laws governing the internal mechanisms of LLMs, pointing toward a systematic framework for understanding and steering these seemingly black-box systems. Such a framework would help overcome their fundamental flaws and enable scientific discoveries beyond human capability.

I am on the academic job market for Fall 2026. If you are interested in my research and would like to discuss potential faculty positions, please feel free to reach out to me via email at chihan3 [at] illinois [dot] edu.

Awards and Honors
News, Service and Experiences
Publications ( show selected / show all by date )
Image
Understanding Emergent In-Context Learning from a Kernel Regression Perspective
Chi Han, Ziqi Wang, Han Zhao, Heng Ji

TMLR 2025, Paper

Image
mCLM: A Function-Infused and Synthesis-Friendly Modular Chemical Language Model
Carl Edwards*, Chi Han*, Gawon Lee, Thao Nguyen, Bowen Jin, Chetan Kumar Prasad, Sara Szymkuć, Bartosz A. Grzybowski, Ying Diao, Jiawei Han, Ge Liu, Hao Peng, Martin D. Burke, Heng Ji

ArXiv Preprint

Image
Computation Mechanism Behind LLM Position Generalization
Chi Han, Heng Ji

ACL 2025, Paper

Image
Eliminating Position Bias of Language Models: A Mechanistic Approach
Ziqi Wang, Hanlin Zhang, Xiner Li, Kuan-Hao Huang, Chi Han, Shuiwang Ji, Sham M. Kakade, Hao Peng, Heng Ji

ICLR 2025, Paper, Twitter

Image
Can Language Models Follow Multiple Turns of Entangled Instructions?
Chi Han,

EMNLP 2025 Findings, Homepage, Paper, Github Repository, HuggingFace Dataset