Hi! I am Yucheng Chu, a Ph.D. student in the Department of Computer Science and Engineering at Michigan State University, where I am advised by Prof. Jiliang Tang.

My research sits at the intersection of large language models, AI for education, and human-centered AI. I am broadly interested in building AI systems that are not only strong in performance, but also reliable, interpretable, and aligned with human judgment. In particular, I work on automated grading, prompt and context optimization, retrieval-augmented generation, and human-in-the-loop learning systems.

A central theme of my recent work is improving how LLMs make evaluative decisions in educational settings. I have developed frameworks such as GradeOpt, GradeHITL, GUIDE, CARO, and GradeRAG, which study rubric optimization, exemplar design, selective human intervention, and structure-aware retrieval for assessment. My goal is to make AI-based educational assessment more accurate, efficient, and pedagogically meaningful.

Before joining MSU, I received a B.S. in Computer Science from Columbia University and a B.A. in Economics and Mathematics from Barnard College.

📝 Publications

Conference and Journal Papers

Optimizing In-Context Demonstrations for LLM-based Automated Grading, Yucheng Chu, Hang Li, Kaiqi Yang, Yasemin Copur-Gencturk, Kevin Haudek, Joseph Krajcik, N. Shin, and Jiliang Tang. In Proceedings of the 27th International Conference on Artificial Intelligence in Education (AIED), 2026.
Confusion-Aware Rubric Optimization for LLM-based Automated Grading, Yucheng Chu, Hang Li, Kaiqi Yang, Yasemin Copur-Gencturk, Joseph Krajcik, N. Shin, and Jiliang Tang. In Proceedings of the 19th International Conference on Educational Data Mining (EDM), 2026.,
From Flat to Structural: Enhancing Automated Short Answer Grading with GraphRAG, Yucheng Chu, Haoyu Han, S. Dong, Hang Li, Kaiqi Yang, Yasemin Copur-Gencturk, Joseph Krajcik, N. Shin, and Hui Liu. In Proceedings of the 19th International Conference on Educational Data Mining (EDM), 2026.
A LLM-Driven Multi-Agent System for Professional Development of Mathematics Teachers, Hang Li, Kaiqi Yang, Yucheng Chu, A. Han, R. Meng, Yasemin Copur-Gencturk, Kevin Haudek, and Hui Liu. In Proceedings of the 27th International Conference on Artificial Intelligence in Education (AIED), 2026.
Coding Complex Datasets by Attending to Qualitative Nuances: A Study on Large Language Model (LLM) Approaches, Yasemin Copur-Gencturk, Kyle Moreno, Yucheng Chu, Hang Li, and Jiliang Tang. ZDM – Mathematics Education, 2026.
Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs, Haoyu Han, K. Guo, Harry Shomer, Y. Wang, Yucheng Chu, Hang Li, L. Ma, and Jiliang Tang. In The Web Conference (WWW), 2026.
A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimization, Yucheng Chu, Hang Li, Kaiqi Yang, Harry Shomer, Hui Liu, Yasemin Copur-Gencturk, and Jiliang Tang. In Proceedings of the 18th International Conference on Educational Data Mining (EDM), 2025.
LLM-Based Automated Grading with Human-in-the-Loop, Yucheng Chu, Hang Li, Kaiqi Yang, Yasemin Copur-Gencturk, and Jiliang Tang. In IEEE International Conference on Engineering, Technology, and Education (TALE), 2025.
Enhancing LLM-Based Short Answer Grading with Retrieval-Augmented Generation, Yucheng Chu, Peng He, Hang Li, Haoyu Han, Kaiqi Yang, Yu Xue, Tingting Li, Joseph Krajcik, and Jiliang Tang. In Proceedings of the 18th International Conference on Educational Data Mining (EDM), 2025.
Ask-Before-Detection: Identifying and Mitigating Conformity Bias in LLM-Powered Error Detector for Math Word Problem Solutions, Hang Li, Tianlong Xu, Kaiqi Yang, Yucheng Chu, Yanling Chen, Yichi Song, Qingsong Wen, and Hui Liu. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025.
Bringing Generative Artificial Intelligence (GenAI) to Education, Hang Li, Kaiqi Yang, Yucheng Chu, and Jiliang Tang. In Proceedings of the 18th International Conference on Educational Data Mining (EDM), 2025.
Iterative LLM-Based Generation and Refinement of Distracting Conditions in Math Word Problems, Kaiqi Yang, Hang Li, Yucheng Chu, Z. Liu, M. Tian, and Hui Liu. In IEEE International Conference on Engineering, Technology, and Education (TALE), 2025.
Content Knowledge Identification with Multi-Agent Large Language Models (LLMs), Kaiqi Yang, Yucheng Chu, Taylor Darwin, A. Han, Hang Li, Hongzhi Wen, Yasemin Copur-Gencturk, Jiliang Tang, and Hui Liu. In Proceedings of the 25th International Conference on Artificial Intelligence in Education (AIED), 2024.

Preprints and Manuscripts

How Uncertain Is the Grade? A Benchmark of Uncertainty Metrics for LLM-Based Automatic Assessment, Hang Li, Kaiqi Yang, X. Long, F. Filippov, Yucheng Chu, Yasemin Copur-Gencturk, Peng He, C. Miller, N. Shin, Joseph Krajcik, Hui Liu, and Jiliang Tang. arXiv preprint, 2026.
A LLM-Driven Multi-Agent Systems for Professional Development of Mathematics Teachers, Kaiqi Yang, Hang Li, Yucheng Chu, A. Han, Yasemin Copur-Gencturk, Jiliang Tang, and Hui Liu. arXiv, 2025.
Unpacking Political Bias in Large Language Models: Insights Across Topic Polarization, Kaiqi Yang, Hang Li, Yucheng Chu, Yuping Lin, Tai-Quan Peng, and Hui Liu. arXiv, 2024.
Beyond Partisan Leaning: A Comparative Analysis of Political Bias in Large Language Models, Tai-Quan Peng, Kaiqi Yang, Sanguk Lee, Hang Li, Yucheng Chu, Yuping Lin, and Hui Liu. arXiv, 2024.