PROFES 2024
Mon 2 - Wed 4 December 2024 Tartu, Estonia

This program is tentative and subject to change.

Large Language Model-based Automated Program Repair (LLM-APR) has recently received significant attention as a debugging assistance. Our objective is to improve the performance of LLM-APR. In this study, we focus on semantic information contained in the source code. Semantic information refers to elements used by the programmer to understand the source code, which does not contribute to compilation or execution.We picked out specification, method names and variable names as semantic information.In the investigation, we prepared eight prompts, each consisting of all combinations of three types of semantic information.The experimental results showed that all semantic information improves the performance of LLM-APR, and variable names are particularly significant.

This program is tentative and subject to change.

Wed 4 Dec

Displayed time zone: Athens change

14:00 - 15:30
PROFES Session 9: AI and ML for Software EngineeringShort Papers and Posters / Research Papers at UT Library - Room 2
14:00
12m
Short-paper
Practical considerations and solutions in NLP-based analysis of code review comments - An experience report
Short Papers and Posters
14:12
12m
Short-paper
Towards Automated Recovery of Links Between Code Commits and Requirements – Initial Results
Short Papers and Posters
Risha Parveen , Ali Mehraj Tampere University, Zheying Zhang Tampere University, Kari Systa Tampere University, Terhi Kilamo Tampere University
14:24
18m
Research paper
Towards Enhancing Task Prioritization in Software Development Through Transformer-Based Issues Classification
Research Papers
Kristian Marison Haugerud University of Oslo, Karthik Shivashankar University of Oslo, Antonio Martini University of Oslo, Norway
14:42
12m
Short-paper
The Effects of Semantic Information on LLM-based Program Repair
Short Papers and Posters
Shota Hori Osaka University, Shinsuke Matsumoto Osaka University, Shinji Kusumoto Osaka University, Yoshiki Higo Osaka University, Kazuya Yasuda Hitachi, Ltd., Shinji Itoh Hitachi, Ltd., Research &Development Group, Phan Thi Thanh Huyen Hitachi, Ltd., Research &Development Group
14:54
36m
Talk
Session 9 Discussion
Research Papers