A Lightweight Intelligent Feedback System for Student Code Submissions Using Large Language Models

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: A Lightweight Intelligent Feedback System for Student Code Submissions Using Large Language Models
Γλώσσα: English
Συγγραφείς: Areej Theeb, Nor Athiyah Abdullah, Ali Fenjan, Pantea Keikhosrokiani
Πηγή: Discover Education. 2026 5.
Διαθεσιμότητα: Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/
Peer Reviewed: Y
Page Count: 17
Ημερομηνία έκδοσης: 2026
Τύπος εγγράφου: Journal Articles
Reports - Research
Descriptors: Feedback (Response), Computer Mediated Communication, Artificial Intelligence, Student Evaluation, Evaluation Methods, Grading, Semantics, Natural Language Processing, Programming, Alternative Assessment, Programming Languages, Evaluation Criteria, Scoring, Formative Evaluation, Tutoring, Computer Science Education
DOI: 10.1007/s44217-026-01400-5
ISSN: 2731-5525
Περίληψη: This study introduces an intelligent, large language model (LLM)-driven feedback system designed to assess and enhance students' programming tasks through semantic comparison and pedagogically contextualized feedback. Unlike traditional grading systems, our system analyzes Python submissions against a reference solution and generates feedback along three main dimensions: logic, style, and performance. The system employs sentence-embedding-based semantic similarity to determine alignment and adaptively adjusts the feedback based on submission quality. Thirty-one student solutions (both reference-level and imperfect submissions) were tested in this study. The results show a mean similarity score of 0.56 (SD = 0.19) and a moderate inverse correlation (r = - 0.65) between feedback length and similarity, confirming adaptive behavior in the system. Visual examination, such as the category-based distribution of feedback, similarity patterns, and solution clustering, further demonstrates the validity and explainability of the system. This approach ensures reproducibility through the transparent definition of reference tasks, embedded similarity scoring and qualitative pattern analysis. The system has implications for AI-facilitated formative feedback, mass code assessment, and adaptive tutoring in computer science education.
Abstractor: As Provided
Σημειώσεις: https://github.com/AreejTheeb/Feedback-System-LLM-Based.git
Entry Date: 2026
Αριθμός Καταχώρησης: EJ1514034
Βάση Δεδομένων: ERIC
Περιγραφή
ISSN:2731-5525
DOI:10.1007/s44217-026-01400-5