AI软件开发中的“偏见异味”：识别公平性债务的潜在来源
Bias Smells in AI Software Development: Recognizing Potential Sources of Fairness Debt
浏览论文内容
中文总结 AI 辅助
该研究通过对某组织四个AI项目的探索性案例研究，识别出六种“偏见异味”指标，将软件异味范式扩展至公平性领域，为将公平性纳入软件质量保证提供了基础。
中文摘要 AI 辅助
背景：公平性债务源于AI开发中的缺陷，可能导致社会危害。技术债务与社会债务分别涉及软件设计决策和团队动态，而公平性债务则涵盖可能加剧基于AI的软件系统中偏见与不平等的开发决策的长期后果。尽管AI公平性受到越来越多关注，但从业者在开发过程中如何识别公平性债务潜在来源的证据有限。目的：本研究调查从业者在基于AI的软件项目中识别为公平性债务潜在来源信号的指标。方法：我们对某组织内的四个AI项目进行了探索性案例研究，通过半结构化访谈和开放式问卷从25名专业人员收集数据，辅以内部沟通渠道和项目文档的观察，并使用迭代定性编码、备忘录撰写和持续比较进行分析。结果：我们确定了六个反复出现的指标，称为“偏见异味”：上下文过度简化、数据集不平衡、指标不足、临时测试、个体多样性意识缺失以及团队构成同质化。这些异味涵盖软件开发的技术和人文方面，标志着可能引入或加剧偏见并导致公平性债务的状况。结论：偏见异味将软件异味范式扩展至公平性领域，为通过可观察指标将公平性纳入软件质量保证提供了基础。
英文摘要
Context: Fairness debt arises from AI development shortcomings that may lead to societal harms. While technical and social debt concern software design decisions and team dynamics, respectively, fairness debt captures the long-term consequences of development decisions that may reinforce bias and inequities in AI-based software systems. Despite growing attention to AI fairness, limited evidence exists on how practitioners recognize potential sources of fairness debt during development. Aim: This study investigates the indicators practitioners recognize as signaling potential sources of fairness debt in AI-based software projects. Method: We conducted an exploratory case study of four AI projects within one organization. Data were collected from 25 professionals through semi-structured interviews and open-ended questionnaires, complemented by observation of internal communication channels and project documentation, and analyzed using iterative qualitative coding, memoing, and constant comparison. Results: We identified six recurring indicators, termed bias smells: Context Oversimplification, Dataset Imbalance, Metrics Inadequacies, Ad hoc Testing, Individual Diversity Unawareness, and Homogeneous Team Composition. These smells span technical and human aspects of software development and signal conditions that may introduce or reinforce bias and contribute to fairness debt. Conclusion: Bias smells extend the software smell paradigm to fairness and provide a foundation for incorporating fairness into software quality assurance through observable indicators.
