WEKO3
アイテム
Fine-tuning Open-Source Large Language Models for Code Documentation Generation: An Evaluation from an Enterprise Perspective
https://ipsj.ixsq.nii.ac.jp/records/2004385
https://ipsj.ixsq.nii.ac.jp/records/2004385a0290d49-bef8-4621-a04b-06807035e3c5
| 名前 / ファイル | ライセンス | アクション |
|---|---|---|
IPSJ-SES2025015.pdf (291.1 KB)
2027年9月9日からダウンロード可能です。
|
Copyright (c) 2025 by the Information Processing Society of Japan
|
|
| 非会員：¥660, IPSJ:学会員：¥330, SE:会員：¥0, DLIB:会員：¥0 | ||
| Item type | Symposium(1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 公開日 | 2025-09-09 | |||||||||
| タイトル | ||||||||||
| 言語 | ja | |||||||||
| タイトル | Fine-tuning Open-Source Large Language Models for Code Documentation Generation: An Evaluation from an Enterprise Perspective | |||||||||
| タイトル | ||||||||||
| 言語 | en | |||||||||
| タイトル | Fine-tuning Open-Source Large Language Models for Code Documentation Generation: An Evaluation from an Enterprise Perspective | |||||||||
| 言語 | ||||||||||
| 言語 | eng | |||||||||
| キーワード | ||||||||||
| 主題Scheme | Other | |||||||||
| 主題 | 企業視点・開発プロセスの実証的分析 | |||||||||
| 資源タイプ | ||||||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||||||
| 資源タイプ | conference paper | |||||||||
| 著者所属 | ||||||||||
| Hitachi, Ltd. | ||||||||||
| 著者所属 | ||||||||||
| Hitachi, Ltd. | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Hitachi, Ltd. | ||||||||||
| 著者所属(英) | ||||||||||
| en | ||||||||||
| Hitachi, Ltd. | ||||||||||
| 著者名 |
Jinan,Dai
× Jinan,Dai
× Shinji,Itoh
|
|||||||||
| 著者名(英) |
Jinan Dai
× Jinan Dai
× Shinji Itoh
|
|||||||||
| 論文抄録(英) | ||||||||||
| 内容記述タイプ | Other | |||||||||
| 内容記述 | Large language models (LLMs) have shown promise in automatic code documentation. However, due to privacy, security, and cost constraints, many enterprise projects are developed and deployed in closed environments, making commercial LLMs inaccessible. As an alternative, open-source LLMs (OpenLLMs) can be considered, but their effectiveness for enterprise applications remains largely unexplored. This study investigates the fine-tuning of OpenLLMs for Japanese enterprise software documentation, addressing challenges such as limited training data, hallucination risks, and language support. Using parameter-efficient fine-tuning and prompt engineering, we demonstrate that fine-tuned OpenLLMs can achieve performance comparable to GPT-4o on real enterprise data. Nevertheless, model performance can be unstable across different prompt settings, and existing automatic evaluation metrics are insufficient for documentation tasks. Our findings highlight the need for improved prompt strategies and specialized evaluation benchmarks for enterprise code documentation. | |||||||||
| 書誌情報 |
ソフトウェアエンジニアリングシンポジウム2025論文集 巻 2025, p. 73-78, 発行日 2025-09-09 |
|||||||||
| 出版者 | ||||||||||
| 言語 | ja | |||||||||
| 出版者 | 情報処理学会 | |||||||||
