CodeLens: A generative ai framework for dynamic feedback on SQL semantic errors

The integration of Generative AI and Machine Learning (ML) technologies in computing education presents a unique opportunity to complement the learning experience for students across different educational levels. This thesis presents an AI-assisted computing framework designed to support engineering students in their learning journey by employing a structured sequence of instructions designed to guide the AI's behavior, fine-tuning techniques and Retrieval Augmented Generation (RAG) models, to deliver helpful feedback tailored to each student’s needs. The framework dynamically adapts to different programming languages by detecting the language used and applying course-specific context through dynamic prompting. Preliminary implementations in courses such as Database Systems have demonstrated the framework’s influence, resulting in a noticeable reduction in SQL problem submissions. This approach acts as an intelligent tutor, providing support to reduce students' frustration, errors, and deepen their understanding of complex engineering problems. The framework’s correctness and effectiveness are evaluated by testing the models on a series of problem sets, with experts assessing and refining the generated responses. Ultimately, this work contributes to the field of Education and Database Systems by showcasing the practical application, adaptability, and effectiveness of AI models in computing education, providing a more supportive learning environment that leads to better outcomes for students tackling computing problems.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Thesis

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Illinois at Urbana-Champaign

Year dc:date

2024

Author dc:creator

• Alrabah, Abdulrahman

Contributors dc:contributor

• Alawini, Abdussalam

• Generative Ai
• Ai
• Machine Learning
• Sql
• Semantic Error
• Feedback System

Statement dc:rights

• Copyright 2024 Abdulrahman AlRabah

Language dc:language

en, eng

Handle dc:identifier

https://hdl.handle.net/2142/127391

OAI record oai:identifier

https://www.ideals.illinois.edu/oai-pmh?verb=GetRecord&metadataPrefix=etdms&identifier=oai%3Awww.ideals.illinois.edu%3A2142%2F127391