CodeLens: a generative ai framework for dynamic feedback on SQL semantic errors
Alrabah, Abdulrahman
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/127391
Description
Title
CodeLens: a generative ai framework for dynamic feedback on SQL semantic errors
Author(s)
Alrabah, Abdulrahman
Issue Date
2024-12-06
Director of Research (if dissertation) or Advisor (if thesis)
Alawini, Abdussalam
Department of Study
Siebel School Comp & Data Sci
Discipline
Computer Science
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
M.S.
Degree Level
Thesis
Keyword(s)
Generative AI, AI, Machine Learning, SQL, semantic error, feedback system
Abstract
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.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
