| アイテムタイプ |
会議発表論文 / Conference Paper(1) |
| 公開日 |
2025-06-20 |
| タイトル |
|
|
タイトル |
Nigerian Software Engineer or American Data Scientist? GitHub Profile Recruitment Bias in Large Language Models |
| 言語 |
|
|
言語 |
eng |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Large Language Models |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
GitHub |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Open Source Software |
| キーワード |
|
|
主題Scheme |
Other |
|
主題 |
Software Team Recruitment |
| 資源タイプ |
|
|
資源タイプ |
conference paper |
| アクセス権 |
|
|
アクセス権 |
embargoed access |
| 著者 |
Nakano, Takashi
嶋利, 一真
Kula, Raula Gaikovina
Treude, Christoph
Cheong, Marc
松本, 健一
|
| 抄録 |
|
|
内容記述タイプ |
Abstract |
|
内容記述 |
Large Language Models (LLMs) have taken the world by storm, demonstrating their ability not only to automate tedious tasks, but also to show some degree of proficiency in completing software engineering tasks. A key concern with LLMs is their “black-box” nature, which obscures their internal workings and could lead to societal biases in their outputs. In the software engineering context, in this early results paper, we empirically explore how well LLMs can automate recruitment tasks for a geographically diverse software team. We use OpenAI's ChatGPT to conduct an initial set of experiments using GitHub User Profiles from four regions to recruit a six-person software development team, analyzing a total of 3,657 profiles over a five-year period (2019$20132023). Results indicate that ChatGPT shows preference for some regions over others, even when swapping the location strings of two profiles (counterfactuals). Furthermore, ChatGPT was more likely to assign certain developer roles to users from a specific country, revealing an implicit bias. Overall, this study reveals insights into the inner workings of LLMs and has implications for mitigating such societal biases in these models. |
| 書誌情報 |
en : Proceedings of the 2024 IEEE International Conference on Software Maintenance and Evolution
p. 624-629,
発行日 2024-12-19
|
| 会議情報 |
|
|
|
会議名 |
2024 IEEE International Conference on Software Maintenance and Evolution |
|
|
主催機関 |
IEEE |
|
|
開始年 |
2024 |
|
|
開始月 |
10 |
|
|
開始日 |
06 |
|
|
終了年 |
2024 |
|
|
終了月 |
10 |
|
|
終了日 |
11 |
|
|
開催期間 |
2024-10-06 - 2024-10-11 |
|
|
開催地 |
Flagstaff, AZ, USA |
|
開催国 |
USA |
| 出版者 |
|
|
出版者 |
IEEE |
| ISSN |
|
|
収録物識別子タイプ |
EISSN |
|
収録物識別子 |
2576-3148 |
| 出版者版DOI |
|
|
関連タイプ |
isVersionOf |
|
|
識別子タイプ |
DOI |
|
|
関連識別子 |
https://doi.org/10.1109/ICSME58944.2024.00063 |
| 出版者版URI |
|
|
関連タイプ |
isVersionOf |
|
|
識別子タイプ |
URI |
|
|
関連識別子 |
https://ieeexplore.ieee.org/abstract/document/10795080 |
| 権利 |
|
|
権利情報 |
Copyright $00A9 2024, IEEE.Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 出版社許諾条件により、本文は2026年12月19日以降に公開 |
| 著者版フラグ |
|
|
出版タイプ |
AM |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
JP20H05706 |
|
|
研究課題名 |
次世代ソフトウェアエコシステムのための基盤・展開技術 |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
JP23K16862 |
|
|
研究課題名 |
ロギング設定の出力に関する分析とプロジェクトの特性に応じた最適化支援 |
| 助成情報 |
|
|
|
助成機関名 |
Japan Society for the Promotion of Science (JSPS) |
|
|
研究課題番号 |
JP23K28065 |
|
|
研究課題名 |
SPDXを活用したソフトウェアエコシステム分析基盤の開発 |
fulltext (229.3 KB)
