Chi Han 韩迟

Email: chihan3 [at] illinois [dot] edu;

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 the science of language models (LMs) by asking and answering the following questions: What role does each hidden representation play in LLMs? When will they malfunction or cause counterintuitive phenomena? How can we adapt the mechanisms to transcend their inherent limits and better serve the downstream tasks? To this end, I have been working on a theoretical and empirical analysis of LLM hidden representations LMs, with the aim to provide insights and develop useful tools and cures for LMs.

I am also committed to fostering inclusivity in AI/ML research. If you’re a student interested in discussing anything related to life, career planning, or research ideas, feel free to email me at my email to schedule a 30-minute meeting. I’d love to connect!

Awards and Honors

[2025 - 2026] Received the Amazon AICE PhD Fellowship.
[2024 - 2025] Received the IBM PhD Fellowship.
[Aug 2024] First-authored paper LM-Steer won an Outstanding Paper Award at ACL 2024. The live demo is hosted at HuggingFace Space.
[Jun 2024] First-authored paper LM-Infinite won an Outstanding Paper Award at NAACL 2024.

News, Service and Experiences

[Feb 2025] Will organize a Tutorial on "The Quest for A Science of Language Models" at AAAI 2025.
[Oct 2024] Gave a guest lecture on "Towards A Physiology of Language Model Representations" at Case West Reserve University.
[Oct 2024] Gave a guest talk at CS 546: Advanced Topics in Natural Language Processing on the science of LMs while serving as a TA.
[Oct 2024] Gave an invited talk at UIUC ML Seminar on "Towards A Physiology of Language Model Representations".
[Sep 2024] Serving as Area Chair for EMNLP 2024 Demos.
[Sep 2024] Our work LM-Infinite and LM-Steer are covered by UIUC News.
[Aug 2024] Obtained my paragliding certificate!
[2024] Co-organizer of UIUC Spring 2024 NLP Seminar series.
[2023-2024] BBQ Co-Chair for the UIUC AI and DAIS group.

Chi Han 韩迟

My Research

Awards and Honors

News, Service and Experiences

Publications ( show selected / show all by date )

Why Does New Knowledge Create Messy Ripple Effects in LLMs?

Jiaxin Qin, Zixuan Zhang, Chi Han, Manling Li, Pengfei Yu, Heng Ji

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models

Chi Han, Qifan Wang, Hao Peng, Wenhan Xiong, Hugo Chan, Heng Ji, Sinong Wang

LM-Steer: Word Embeddings Are Steers for Language Models

Chi Han, Jialiang Xu, Manling Li, Yi Ren Fung, Chenkai Sun, Nan Jiang, Tarek Abdelzaher, Heng Ji

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

Rui Pan, Xiang Liu, Shizhe Diao, Renjie Pi, Jipeng Zhang, Chi Han, Tong Zhang

Large Language Models on Graphs: A Comprehensive Survey

Bowen Jin, Gang Liu, Chi Han, Meng Jiang, Heng Ji, Jiawei Han,

CREATOR: Disentangling Abstract and Concrete Reasonings of Large Language Models through Tool Creation

Cheng Qian, Chi Han, Yi Ren Fung, Yujia Qin, Zhiyuan Liu, Heng Ji,

Explaining Emergent In-Context Learning as Kernel Regression

Chi Han, Ziqi Wang, Han Zhao, Heng Ji

Understanding the Effect of Data Augmentation on Knowledge Distillation

Ziqi Wang, Chi Han, Wenxuan Bao, Heng Ji

Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning

Chi Han, Qizheng He, Charles Yu, Xinya Du, Tonghang Hang, Heng Ji

Zero-Shot Classification by Logical Reasoning on Natural Language Explanations

Chi Han, Hengzhi Pei, Xinya Du, Heng Ji

Learning Shared Semantic Space for Speech-to-Text Translation

Chi Han, Mingxuan Wang, Lei Li, Heng Ji

Visual Concept-Metaconcept Learning

Chi Han, Jiayuan Mao, Chuang Gan, Joshua B. Tenenbaum, Jiajun Wu,

Chi Han 韩迟

My Research

Awards and Honors

News, Service and Experiences

Publications ( show selected / show all by date )

Why Does New Knowledge Create Messy Ripple Effects in LLMs?

Jiaxin Qin, Zixuan Zhang, Chi Han, Manling Li, Pengfei Yu, Heng Ji

LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models

Chi Han, Qifan Wang, Hao Peng, Wenhan Xiong, Hugo Chan, Heng Ji, Sinong Wang

LM-Steer: Word Embeddings Are Steers for Language Models

Chi Han, Jialiang Xu, Manling Li, Yi Ren Fung, Chenkai Sun, Nan Jiang, Tarek Abdelzaher, Heng Ji

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning

Rui Pan, Xiang Liu, Shizhe Diao, Renjie Pi, Jipeng Zhang, Chi Han, Tong Zhang

Large Language Models on Graphs: A Comprehensive Survey

Bowen Jin, Gang Liu, Chi Han, Meng Jiang, Heng Ji, Jiawei Han,

CREATOR: Disentangling Abstract and Concrete Reasonings of Large Language Models through Tool Creation

Cheng Qian, Chi Han, Yi Ren Fung, Yujia Qin, Zhiyuan Liu, Heng Ji,

Explaining Emergent In-Context Learning as Kernel Regression

Chi Han, Ziqi Wang, Han Zhao, Heng Ji

Understanding the Effect of Data Augmentation on Knowledge Distillation

Ziqi Wang, Chi Han, Wenxuan Bao, Heng Ji

Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning

Chi Han, Qizheng He, Charles Yu, Xinya Du, Tonghang Hang, Heng Ji

Zero-Shot Classification by Logical Reasoning on Natural Language Explanations

Chi Han, Hengzhi Pei, Xinya Du, Heng Ji

Learning Shared Semantic Space for Speech-to-Text Translation

Chi Han, Mingxuan Wang, Lei Li, Heng Ji

Visual Concept-Metaconcept Learning

Chi Han*, Jiayuan Mao*, Chuang Gan, Joshua B. Tenenbaum, Jiajun Wu,

Chi Han, Jiayuan Mao, Chuang Gan, Joshua B. Tenenbaum, Jiajun Wu,