APSEC 2024 (series) / ERA - Early Research Achievements /
Enhancing Source Code Comment Generation via Retrieval-Augmented Generation with Design Document Term Dictionary
This program is tentative and subject to change.
Thu 5 Dec 2024 17:00 - 17:20 at Room 3 (Xiangquan Ballroom) - Session (14)
Effective software development depends on clear code comments for better understanding. We introduce a new method for generating automated source code comments using Retrieval-Augmented Generation (RAG) with a Design Document Term Dictionary (DDTD). This method aligns terms and their meanings from design documents with lines of source code, producing comments that clearly reflect the code’s intent and functionality. Our evaluations on the open-source ERP software iDempiere show significant improvements: Context Precision increased by 22% and Faithfulness by 17% compared to conventional RAG methods These results confirm our method’s validity. Therefore, we plan to explore its application to different software contexts in future work.
This program is tentative and subject to change.
Thu 5 DecDisplayed time zone: Beijing, Chongqing, Hong Kong, Urumqi change
Thu 5 Dec
Displayed time zone: Beijing, Chongqing, Hong Kong, Urumqi change
16:00 - 17:30 | |||
16:00 30mTalk | Improving Code Search with Hard Negative Sampling Based on Fine-tuning Technical Track Hande Dong International Digital Economy Academy, Jiayi Lin International Digital Economy Academy, Yanlin Wang Sun Yat-sen University, Yichong Leng University of Science and Technology of China, Jiawei Chen Zhejiang University, Yutao Xie International Digital Economy Academy | ||
16:30 30mTalk | HANTracer: Leveraging Heterogeneous Graph Attention Network for Large-Scale Requirements-Code Traceability Link Recovery Technical Track Zhiyuan Zou , Bangchao Wang Wuhan Textile University, Hongyan Wan Wuhan Textile University, Huan Jin Wuhan Textile University, Xiaoxiao Li School of Computer Science and Artificial Intelligence, Wuhan Textile University, Yukun Cao School of Computer Science and Artificial Intelligence, Wuhan Textile University | ||
17:00 20mTalk | Enhancing Source Code Comment Generation via Retrieval-Augmented Generation with Design Document Term Dictionary ERA - Early Research Achievements Kazu Nishikawa Hitachi, Ltd. Research & Development Group., Genta Koreki Hitachi, Ltd. Research & Development Group., Hideyuki Kanuka Hitachi, Ltd. |