Publications

Selected papers grouped by year. For citations and updates, see my Google Scholar profile.

2026

  1. Chapagain, J., & Rus, V. Enhancing Intelligent Tutoring Systems with Instruction-Tuned LLMs: Automated Assessment of Student Code Comprehension International Conference on Artificial Intelligence in Education(AIED) 2026
  2. Sajib, M. I., Tamang, S., Chapagain, J., & Rus, V. A Study on How Free Use of LLMs Assists Novices with Code Comprehension Tasks The International FLAIRS Conference Proceedings, 39(1). https://doi.org/10.32473/flairs.39.1.141647e

2025

  1. Chapagain, J., & Rus, V. Automated assessment of student self-explanation in code comprehension using pre-trained language models. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 39, No. 28, pp. 28996-29003.
  2. Chapagain, J., Narayanan, A. B. L., Akhuseyinoglu, K., Brusilovsky, P., & Rus, V. SelfCode 2.0: An Annotated Corpus of Student and Expert Line-by-Line Explanations of Code for Automated Assessment.
  3. Neupane, S., Chapagain, J., Niraula, N. B., & Koirala, D. Generative AI for Named Entity Recognition in Low-Resource Language Nepali. arXiv:2503.09822.

2024

  1. Khanal, K., & Chapagain, J. Curating LLM Tuning Data from the FineWeb Dataset for High-fidelity Domain Adaptation. AGU24.
  2. Chapagain, J., Sajib, M. I., Prodan, R., & Rus, V. A Study of LLM Generated Line-by-Line Explanations in the Context of Conversational Program Comprehension Tutoring Systems. European Conference on Technology Enhanced Learning (pp. 64-74), Springer.

2023

  1. Brusilovsky, P., Lekshmi-Narayanan, A. B., Oli, P., Chapagain, J., Hassany, M., Banjade, R., & Rus, V. Explaining code examples in introductory programming courses: LLM vs humans. arXiv:2403.05538.
  2. Oli, P., Banjade, R., Chapagain, J., & Rus, V. Automated Assessment of Students' Code Comprehension using LLMs. arXiv:2401.05399.
  3. Oli, P., Banjade, R., Chapagain, J., & Rus, V. The Behavior of Large Language Models When Prompted to Generate Code Explanations. GAIED @ NeurIPS 2023, arXiv.
  4. Oli, P., Banjade, R., Lekshmi Narayanan, A. B., Chapagain, J., Tamang, L. J., Brusilovsky, P., & Rus, V. Improving Code Comprehension Through Scaffolded Self-explanations. AIED (pp. 478-483), Springer.
  5. Niraula, N., & Chapagain, J. DanfeNER - Named Entity Recognition in Nepali Tweets. The International FLAIRS Conference Proceedings, 36(1). DOI: 10.32473/flairs.36.133384.
  6. Chapagain, J., Risha, Z., Banjade, R., Oli, P., Tamang, L., Brusilovsky, P., & Rus, V. SelfCode: An Annotated Corpus and a Model for Automated Assessment of Self-Explanation During Source Code Comprehension. The International FLAIRS Conference Proceedings, 36(1).

2022

  1. Niraula, N., & Chapagain, J. Named Entity Recognition for Nepali: Data Sets and Algorithms. The International FLAIRS Conference Proceedings, Vol. 35.
  2. Chapagain, J., Tamang, L., Banjade, R., Oli, P., & Rus, V. Automated Assessment of Student Self-explanation During Source Code Comprehension. The International FLAIRS Conference Proceedings, Vol. 35.
  3. Tamang, L. J., Banjade, R., Chapagain, J., & Rus, V. Automatic Question Generation for Scaffolding Self-explanations for Code Comprehension. AIED 2022, Part I, pp. 743-748, Springer.

2021

  1. Banjade, R. Domain model discovery from textbooks for computer programming intelligent tutors. The International FLAIRS Conference Proceedings, Vol. 34.
  2. Rus, V., Akhuseyinoglu, K., Chapagain, J., Tamang, L., & Brusilovsky, P. Prompting for Free Self-Explanations Promotes Better Code Comprehension. Proceedings of the 5th CSEDM Workshop.