Commit messages in a version control system provide valuable information for developers regarding code changes in software systems. Commit messages can be the only source of information left for future developers describing what was changed and why. However, writing high-quality commit messages is often neglected in practice. Large Language Model (LLM) generated commit messages have emerged as a way to mitigate this issue. We introduce the AI-Powered Commit Explorer (APCE), a tool to support developers and researchers in the use and study of LLM-generated commit messages. APCE gives researchers the option to store different prompts for LLMs and provides an additional evaluation prompt that can further enhance the commit message provided by LLMs. APCE also provides researchers with a straightforward method for humans to assess LLM-generated messages on a set of criteria. Demo link https://youtu.be/zYrJ9s6sZvo
Wed 10 SepDisplayed time zone: Auckland, Wellington change
10:30 - 12:00 | Session 2 - Quality Assurance 1Tool Demonstration Track / Research Papers Track / Industry Track / NIER Track / Journal First Track at Case Room 2 260-057 Chair(s): Coen De Roover Vrije Universiteit Brussel | ||
10:30 15m | A Jump-Table-Agnostic Switch Recovery on ASTs Research Papers Track | ||
10:45 15m | Quantization Is Not a Dealbreaker: Empirical Insights from Large Code Models Research Papers Track Saima Afrin William & Mary, Antonio Mastropaolo William and Mary, USA, Bowen Xu North Carolina State University Pre-print | ||
11:00 10m | AI-Powered Commit Explorer (APCE) Tool Demonstration Track Yousab Grees Belmont University, Polina Iaremchuk Belmont University, Ramtin Ehsani Drexel University, Esteban Parra Rodriguez Belmont University, Preetha Chatterjee Drexel University, USA, Sonia Haiduc Florida State University Pre-print | ||
11:10 10m | JDala - A Simple Capability System for Java Tool Demonstration Track Quinten Smit Victoria University of Wellington, Jens Dietrich Victoria University of Wellington, Michael Homer Victoria University of Wellington, Andrew Fawcet Victoria University of Wellington, James Noble Independent. Wellington, NZ | ||
11:20 10m | ExpertCache: GPU-Efficient MoE Inference through Reinforcement Learning-Guided Expert Selection NIER Track Xunzhu Tang University of Luxembourg, Tiezhu Sun University of Luxembourg, Yewei Song University of Luxembourg, SiYuanMa , Jacques Klein University of Luxembourg, Tegawendé F. Bissyandé University of Luxembourg | ||
11:30 15m | Efficient Detection of Intermittent Job Failures Using Few-Shot Learning Industry Track Henri Aïdasso École de technologie supérieure (ÉTS), Francis Bordeleau École de Technologie Supérieure (ETS), Ali Tizghadam TELUS Pre-print | ||
11:45 15m | LogOW: A Semi-Supervised Log Anomaly Detection Model in Open-World Setting Journal First Track Jingwei Ye Nankai University, Chunbo Liu Civil Aviation University of China, Zhaojun Gu Civil Aviation University of China, Zhikai Zhang Civil Aviation University of China, Xuying Meng The Institute of Computing Technology, Chinese Academy of Sciences, Weiyao Zhang The Institute of Computing Technology, Chinese Academy of Sciences, Yujun Zhang The Institute of Computing Technology, Chinese Academy of Sciences | ||