An in-depth study of software library upgrade dependency issues
With the rapid advancements in Artificial Intelligence and Large Language Models, the potential to leverage cutting-edge AI for addressing code-related issues is continually growing. This study explores the potential of utilizing AI and evaluate its effectiveness in resolving software dependen...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/181284 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-181284 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1812842024-11-22T11:09:55Z An in-depth study of software library upgrade dependency issues Leow, Wei Jie Li Yi (SCSE) College of Computing and Data Science yi_li@ntu.edu.sg Computer and Information Science With the rapid advancements in Artificial Intelligence and Large Language Models, the potential to leverage cutting-edge AI for addressing code-related issues is continually growing. This study explores the potential of utilizing AI and evaluate its effectiveness in resolving software dependency upgrade incompatibility issues. We developed an Automated Repair Program SLUDI and evaluated the effectiveness of three different large language models against a dataset of 30 upgrade incompatibility issues. Results show that the models achieved an average of 38.9% identification rate and 41.1% correctness rate. The evaluation results show that given only the exception information, source code of the method, context of the library upgraded, the large language models are not very effective in resolving software dependency upgrade incompatibility issues. Future research recommendations include extracting and providing more crucial information to the AI, enabling them to gain a deeper understanding of the project, which could improve their ability to identify and fix the incompatibility issue with greater accuracy. Exploring automatic repair methods could also be implemented to enhance efficiency and reduce the potential for human error. Bachelor's degree 2024-11-22T11:09:54Z 2024-11-22T11:09:54Z 2024 Final Year Project (FYP) Leow, W. J. (2024). An in-depth study of software library upgrade dependency issues. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/181284 https://hdl.handle.net/10356/181284 en SC4079 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Computer and Information Science |
spellingShingle |
Computer and Information Science Leow, Wei Jie An in-depth study of software library upgrade dependency issues |
description |
With the rapid advancements in Artificial Intelligence and Large Language Models, the
potential to leverage cutting-edge AI for addressing code-related issues is continually growing.
This study explores the potential of utilizing AI and evaluate its effectiveness in resolving
software dependency upgrade incompatibility issues. We developed an Automated Repair
Program SLUDI and evaluated the effectiveness of three different large language models
against a dataset of 30 upgrade incompatibility issues. Results show that the models achieved
an average of 38.9% identification rate and 41.1% correctness rate. The evaluation results show
that given only the exception information, source code of the method, context of the library
upgraded, the large language models are not very effective in resolving software dependency
upgrade incompatibility issues. Future research recommendations include extracting and
providing more crucial information to the AI, enabling them to gain a deeper understanding of
the project, which could improve their ability to identify and fix the incompatibility issue with
greater accuracy. Exploring automatic repair methods could also be implemented to enhance
efficiency and reduce the potential for human error. |
author2 |
Li Yi (SCSE) |
author_facet |
Li Yi (SCSE) Leow, Wei Jie |
format |
Final Year Project |
author |
Leow, Wei Jie |
author_sort |
Leow, Wei Jie |
title |
An in-depth study of software library upgrade dependency issues |
title_short |
An in-depth study of software library upgrade dependency issues |
title_full |
An in-depth study of software library upgrade dependency issues |
title_fullStr |
An in-depth study of software library upgrade dependency issues |
title_full_unstemmed |
An in-depth study of software library upgrade dependency issues |
title_sort |
in-depth study of software library upgrade dependency issues |
publisher |
Nanyang Technological University |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/181284 |
_version_ |
1816859065184157696 |