Abstract
In this paper, we explore the application of large language models (LLMs) for generating code-tracing questions in introductory programming courses. We designed targeted prompts for GPT4, guiding it to generate code-tracing questions based on code snippets and descriptions. We established a set of human evaluation metrics to assess the quality of questions produced by the model compared to those created by human experts. Our analysis provides insights into the capabilities and potential of LLMs in generating diverse code-tracing questions. Additionally, we present a unique dataset of human and LLM-generated tracing questions, serving as a valuable resource for both the education and NLP research communities. This work contributes to the ongoing dialogue on the potential uses of LLMs in educational settings.- Anthology ID:
- 2023.findings-emnlp.496
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2023
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 7406–7421
- Language:
- URL:
- https://aclanthology.org/2023.findings-emnlp.496
- DOI:
- 10.18653/v1/2023.findings-emnlp.496
- Cite (ACL):
- Aysa Fan, Haoran Zhang, Luc Paquette, and Rui Zhang. 2023. Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7406–7421, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Exploring the Potential of Large Language Models in Generating Code-Tracing Questions for Introductory Programming Courses (Fan et al., Findings 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2023.findings-emnlp.496.pdf