Automated Program Repair using Large Language Models (LLMs)

Simple item page
dc.contributor.authorAmina, MEKIDECHE
dc.contributor.authorAmani, DJAIDJA
dc.contributor.authorSupervisor: Hichem, DEBBI
dc.date.accessioned2025-07-07T14:12:32Z
dc.date.available2025-07-07T14:12:32Z
dc.date.issued2025-06-15
dc.description.abstractThis work proposes an approach to APR by integrating a fine-tuned CodeLLaMA-7b model with a GraphRAG-based retrieval framework. We first applied LoRA to fine-tune the CodeLLaMA model using the domain-specific RepairLLaMA dataset. To enhance contextual awareness, we built a graph-based retriever that combines CodeBERT-generated embeddings with structural relationships between buggy and fixed code pairs from the Defects4J dataset. Our system prioritizes relevant repair examples and enables efficient retrieval of code context. Additionally, we developed a simple web interface to provide real-time bug fix suggestions, demonstrating the practical applicability of our pipeline.
dc.identifier.urihttps://repository.univ-msila.dz/handle/123456789/46725
dc.language.isoen
dc.publisherMohamed Boudiaf University of M'sila
dc.subjectLarge Language Models
dc.subjectAutomated Program Repair
dc.subjectGraphRAG
dc.subjectFine-tuning
dc.titleAutomated Program Repair using Large Language Models (LLMs)
dc.typeThesis

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Amina MEKIDECHE, Amani DJAIDJA.pdf
Size:
2.29 MB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Master Thesis