Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education
arXiv:2605.21614v1 Announce Type: cross Abstract: 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
The rapid advancement and accessibility of large language models are enabling their application to automate tasks previously requiring human intelligence, such as educational assessment.
Automated assessment of complex student responses has historically been a bottleneck in scaling personalized education, and LLMs offer a potential solution to this challenge.
The ability to automatically assess nuanced open-ended student explanations could significantly enhance the scalability and effectiveness of active learning pedagogies.
- · EdTech companies
- · Programming education platforms
- · Students
- · Educators
- · Manual grading services
- · Traditional assessment providers
Increased adoption of active learning methodologies in programming education.
Improved student learning outcomes due to more frequent and personalized feedback.
Potential for LLMs to automate assessment across a broader range of complex subjects beyond programming.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG