用辩论式框架透明检测算法偏见，提升公平性可解释性。
Argumentative Debates for Transparent Bias Detection [Technical Report]
- 将偏见检测设计为基于论点图的辩论过程，增强透明度。
- 在局部邻域群体成功率与重要性上构建可解释论点，实现精准检测。
- 适合关注算法公平性与可解释性的研究人员和开发者。
随着人工智能在社会中的广泛应用，应对新兴偏见以防止系统性歧视至关重要。尽管已有多种偏见检测方法提出，但多数忽略透明性。可解释性与可解释性对算法公平性而言尤为关键，因其具有强人本导向。本文提出ABIDE（Argumentative BIas detection by DEbate），一种新型框架，将偏见检测以辩论形式透明呈现，其基础为形式与计算论证中的论点图。论点聚焦于局部邻域内群体的成功概率及其邻域的重要性。实验评估表明，ABIDE在性能上优于基准辩论方法，展现出显著优势。
原文摘要 · Abstract (English)
As the use of AI in society grows, addressing emerging biases is essential to prevent systematic discrimination. Several bias detection methods have been proposed, but, with few exceptions, these tend to ignore transparency. Instead, interpretability and explainability are core requirements for algorithmic fairness, even more so than for other algorithmic solutions, given the human-oriented nature of fairness. We present ABIDE (Argumentative BIas detection by DEbate), a novel framework that structures bias detection transparently as debate, guided by an underlying argument graph as understood in (formal and computational) argumentation. The arguments are about the success chances of groups in local neighbourhoods and the significance of these neighbourhoods. We evaluate ABIDE experimentally and demonstrate its strengths in performance against an argumentative baseline.
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。