Using LLMs for Knowledge Component-level Correctness Labeling in Open-ended Coding Problems

This repository contains the code for the paper Using LLMs for Knowledge Component-level Correctness Labeling in Open-ended Coding Problems. To our knowledge, this work is the first work to explore the use of LLMs for KC-level correctness labeling in student-written code. It shows better fit to the Power law of Practice than using problem-level correctness for student modeling.

If you use our code or find this work useful in your research then please cite us!

@misc{duan2026usingllmsknowledgecomponentlevel,
      title={Using LLMs for Knowledge Component-level Correctness Labeling in Open-ended Coding Problems}, 
      author={Zhangqi Duan and Arnav Kankaria and Dhruv Kartik and Andrew Lan},
      year={2026},
      eprint={2602.17542},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2602.17542}, 
}