Enhancing Source Code Comment Generation via Retrieval-Augmented Generation with Design Document Term Dictionary

Effective software development depends on clear code comments for better understanding. We introduce a method for generating automated source-code comments using retrieval-augmented generation (RAG) with a design document term dictionary. This method aligns terms and their meanings from design documents with lines of source code, producing comments that clearly reflect the source-code's intent and functionality. Our evaluations on the open-source software iDempiere show significant improvements: context precision increased by 22% and faithfulness by 17 % compared with conventional RAG methods These results confirm our method's validity. Therefore, we plan to explore its application to different software contexts in future work.