Chronologic: Measuring Language Models’ Ability To Represent The Past
arXiv preprint, 2026.
About Me
Hi there! I'm Ziliang Qiu (丘子靓), a second-year Ph.D. student in the School of Information Sciences at the University of Illinois Urbana-Champaign (UIUC), advised by Ted Underwood.
My research focuses on computational literary studies, where I apply natural language processing to the analysis of literary texts while keeping humanistic questions at the center. I'm also interested in model-generated language, particularly its diversity and creativity.
Before coming to Illinois, I received my M.A. in Linguistics and Applied Linguistics from the Institute of Chinese Information Processing at Beijing Normal University, where I was advised by Zhiying Liu and Renfen Hu. I earned my B.A. in Chinese Linguistics from Central China Normal University.
Publications
2026
Applications Of Text Similarity Computation In Digital Humanities Research: A Review Of The 5th Beijing Digital Humanities Workshop
数字人文 [Journal of Digital Humanities], (3).
Learning Self-Correction In Vision-Language Models Via Rollout Augmentation
Proceedings of the 43rd International Conference on Machine Learning ICML 2026
2025
Deep Associations, High Creativity: A Simple Yet Effective Metric For Evaluating Large Language Models
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pp. 10859–10872. EMNLP 2025
Education
Ph.D. in Information Sciences
School of Information Sciences, University of Illinois Urbana-Champaign
Advisor: Ted Underwood · In progress
M.A. in Linguistics and Applied Linguistics
2022–2025
Institute of Chinese Information Processing, Beijing Normal University
Advisors: Zhiying Liu and Renfen Hu
B.A. in Chinese Linguistics
2018–2022
Central China Normal University