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.

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.

Awards and Honors
News, Service and Experiences
  • [Oct 2024] Gave an invited talk at UIUC CS 591 MLR seminar on "Towards A Physiology of Language Model Representations".
  • [Sep 2024] Gave a lightning talk at AICE Symposium on "Towards A Physiology of Language Model Representations".
  • [Sep 2024] Serving as Area Chair for EMNLP 2024 Demos.
  • [Sep 2024] Co-organizing "Towards Knowledgeable Foundation Models" workshop at AAAI-2025.
  • [Sep 2024] Our work LM-Infinite and LM-Steer are covered by UIUC News.
  • [Aug 2024] Obtained my solo paragliding certificate!
  • [Fall 2024] Teaching assistant for CS 546: Advanced Topics in Natural Language Processing, with a guest talk on the science of LMs.
  • [Jun 2024] I gave one talk on "LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models" at AI Time.
  • [2024] Co-organizer of UIUC Spring 2024 NLP Seminar series.
  • [2023-2024] BBQ Co-Chair for the UIUC AI and DAIS group.
  • [Dec 2023] I gave one talk at Data Intelligence.
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

EMNLP 2024 Short, Paper

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

NAACL 2024 (Outstanding Paper Award), Paper, Codes, Video

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

ACL 2024 (Outstanding Paper Award), Paper, Codes, HuggingFace Live Demo, Slides, Poster

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

Arxiv, Paper, Codes

Large Language Models on Graphs: A Comprehensive Survey
Bowen Jin, Gang Liu, Chi Han, Meng Jiang, Heng Ji, Jiawei Han,

TKDE, Paper, Github Repo: "Awesome Language Model on Graphs"

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,

EMNLP Findings, Paper, Codes

Explaining Emergent In-Context Learning as Kernel Regression
Chi Han, Ziqi Wang, Han Zhao, Heng Ji

ArXiv, Paper

Understanding the Effect of Data Augmentation on Knowledge Distillation
Ziqi Wang, Chi Han, Wenxuan Bao, Heng Ji

ArXiv, Paper

Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning
Chi Han, Qizheng He, Charles Yu, Xinya Du, Tonghang Hang, Heng Ji

ICLR 2023, Paper, Codes

Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Chi Han, Hengzhi Pei, Xinya Du, Heng Ji

ACL 2023 Findings, Paper, Codes

Learning Shared Semantic Space for Speech-to-Text Translation
Chi Han, Mingxuan Wang, Lei Li, Heng Ji

ACL 2021 Findings, Paper, Codes

Visual Concept-Metaconcept Learning
Chi Han*, Jiayuan Mao*, Chuang Gan, Joshua B. Tenenbaum, Jiajun Wu,

NeurIPS 2019, Paper, Codes, Project Page