Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918515615727616 |
|---|---|
| author | Lekshmi-Narayanan, Arun-Balajiee Hassany, Mohammad Brusilovsky, Peter |
| author_facet | Lekshmi-Narayanan, Arun-Balajiee Hassany, Mohammad Brusilovsky, Peter |
| contents | Worked examples are step-by-step solutions to problems in a specific domain, offered to students to acquire domain-specific problem-solving skills. The effectiveness of worked examples could be enhanced by combining them with self-explanations, which ask students to explain rather than passively study each problem-solving step. The main challenge of this approach is assessing the correctness of the student's explanations. In the prevailing approach, student explanations are judged by their semantic similarity to an instructor's or domain expert's explanation. Given recent advances in LLM-based automated scoring, it remains unclear whether semantic similarity methods are still the most effective technique to automatically score textual student responses like essays or code explanations. Comparing these methods also requires quality datasets that offer distinctive features such as balanced class distributions and domain-specific labeled data for automated scoring tasks. In this paper, we present a rigorous comparison between LLMs and semantic similarity used for automated scoring, framed as a binary classification task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21614 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education Lekshmi-Narayanan, Arun-Balajiee Hassany, Mohammad Brusilovsky, Peter Human-Computer Interaction Machine Learning Worked examples are step-by-step solutions to problems in a specific domain, offered to students to acquire domain-specific problem-solving skills. The effectiveness of worked examples could be enhanced by combining them with self-explanations, which ask students to explain rather than passively study each problem-solving step. The main challenge of this approach is assessing the correctness of the student's explanations. In the prevailing approach, student explanations are judged by their semantic similarity to an instructor's or domain expert's explanation. Given recent advances in LLM-based automated scoring, it remains unclear whether semantic similarity methods are still the most effective technique to automatically score textual student responses like essays or code explanations. Comparing these methods also requires quality datasets that offer distinctive features such as balanced class distributions and domain-specific labeled data for automated scoring tasks. In this paper, we present a rigorous comparison between LLMs and semantic similarity used for automated scoring, framed as a binary classification task. |
| title | Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education |
| topic | Human-Computer Interaction Machine Learning |
| url | https://arxiv.org/abs/2605.21614 |