Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.12216 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929762075672576 |
|---|---|
| author | Smith IV, David H. Fowler, Max Denny, Paul Zilles, Craig |
| author_facet | Smith IV, David H. Fowler, Max Denny, Paul Zilles, Craig |
| contents | Reading and understanding code are fundamental skills for novice programmers, and especially important with the growing prevalence of AI-generated code and the need to evaluate its accuracy and reliability. ``Explain in Plain English'' questions are a widely used approach for assessing code comprehension, but providing automated feedback, particularly on comprehension levels, is a challenging task. This paper introduces a novel method for automatically assessing the comprehension level of responses to ``Explain in Plain English'' questions. Central to this is the ability to distinguish between two response types: multi-structural, where students describe the code line-by-line, and relational, where they explain the code's overall purpose. Using a Large Language Model (LLM) to segment both the student's description and the code, we aim to determine whether the student describes each line individually (many segments) or the code as a whole (fewer segments). We evaluate this approach's effectiveness by comparing segmentation results with human classifications, achieving substantial agreement. We conclude with how this approach, which we release as an open source Python package, could be used as a formative feedback mechanism. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_12216 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Counting the Trees in the Forest: Evaluating Prompt Segmentation for Classifying Code Comprehension Level Smith IV, David H. Fowler, Max Denny, Paul Zilles, Craig Computers and Society Software Engineering Reading and understanding code are fundamental skills for novice programmers, and especially important with the growing prevalence of AI-generated code and the need to evaluate its accuracy and reliability. ``Explain in Plain English'' questions are a widely used approach for assessing code comprehension, but providing automated feedback, particularly on comprehension levels, is a challenging task. This paper introduces a novel method for automatically assessing the comprehension level of responses to ``Explain in Plain English'' questions. Central to this is the ability to distinguish between two response types: multi-structural, where students describe the code line-by-line, and relational, where they explain the code's overall purpose. Using a Large Language Model (LLM) to segment both the student's description and the code, we aim to determine whether the student describes each line individually (many segments) or the code as a whole (fewer segments). We evaluate this approach's effectiveness by comparing segmentation results with human classifications, achieving substantial agreement. We conclude with how this approach, which we release as an open source Python package, could be used as a formative feedback mechanism. |
| title | Counting the Trees in the Forest: Evaluating Prompt Segmentation for Classifying Code Comprehension Level |
| topic | Computers and Society Software Engineering |
| url | https://arxiv.org/abs/2503.12216 |