发现并修复了用户界面中阻碍特定用户群体的AI包容性缺陷。
"Over-the-Hood" AI Inclusivity Bugs and How 3 AI Product Teams Found and Fixed Them
- 通过实地调研3个AI团队，识别出6类用户端AI包容性缺陷。
- 共发现83次缺陷实例，其中47个已成功修复。
- 改进了原有设计方法，提出专用于AI产品的GenderMag-for-AI工具。
尽管已有大量研究揭示了AI的“隐性偏见”（如算法、训练数据等），但“显性包容性偏见”——即用户界面中对特定问题解决方式用户的排斥性障碍——仍缺乏系统探讨。本研究通过对3个AI产品团队开展实地调查，探索用户端AI产品中特有的包容性缺陷类型、出现频率及修复路径。研究发现共存在6类AI包容性缺陷，总计出现83次；团队通过实践修复了其中47个实例。在此基础上，提出一种针对AI场景优化的包容性设计方法变体——GenderMag-for-AI，能更有效识别特定类型的包容性缺陷。
原文摘要 · Abstract (English)
While much research has shown the presence of AI's "under-the-hood" biases (e.g., algorithmic, training data, etc.), what about "over-the-hood" inclusivity biases: barriers in user-facing AI products that disproportionately exclude users with certain problem-solving approaches? Recent research has begun to report the existence of such biases -- but what do they look like, how prevalent are they, and how can developers find and fix them? To find out, we conducted a field study with 3 AI product teams, to investigate what kinds of AI inclusivity bugs exist uniquely in user-facing AI products, and whether/how AI product teams might harness an existing (non-AI-oriented) inclusive design method to find and fix them. The teams' work resulted in identifying 6 types of AI inclusivity bugs arising 83 times, fixes covering 47 of these bug instances, and a new variation of the GenderMag inclusive design method, GenderMag-for-AI, that is especially effective at detecting certain kinds of AI inclusivity bugs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。