论因果关系在公平性中的必要性与适用性：一个面向AI审计与法律分析的统一框架

使用无监督偏见检测工具审计荷兰公共部门风险评估算法

Auditing a Dutch Public Sector Risk Profiling Algorithm Using an Unsupervised Bias Detection Tool

本文通过无监督偏见检测工具审计荷兰公共部门风险评估算法，揭示非欧洲移民学生与本地学生间的偏见差异，并提供开源工具用于后续偏见审计。

这很复杂。欧盟人工智能法案中高风险系统中算法公平与非歧视规定的相互关系

It's complicated. The relationship of algorithmic fairness and non-discrimination provisions for high-risk systems in the EU AI Act

本文探讨欧盟人工智能法案中高风险系统中算法公平与非歧视规定的相互关系，分析两者之间的联系及未来可能的互动。

在线社交媒体审计的数学框架

Mathematical Framework for Online Social Media Auditing

本文提出在线社交媒体审计的数学框架，并构建带样本复杂度保证的数据驱动统计审计程序，用于监管算法过滤对用户信念的偏转，可供外部监管者或平台自审使用。

Promises and Challenges of Causality for Ethical Machine Learning

In recent years, there has been increasing interest in causal reasoning for designing fair decision-making systems due to its compatibility with legal frameworks, interpretability for human stakeholders, and robustness to spurious correlations inherent in observational data, among other factors. The recent attention to causal fairness, however, has been accompanied with great skepticism due to practical and epistemological challenges with applying current causal fairness approaches in the literature. Motivated by the long-standing empirical work on causality in econometrics, social sciences, a…

因果驱动的模型鲁棒性审计

Causality-Driven Audits of Model Robustness

本文提出一种基于因果推断的DNN鲁棒性审计新方法，通过因果模型编码成像因素及其交互，仅用观测数据估计各因素对性能的因果效应，以应对真实世界复杂失真，降低部署风险。

CoGS：使用目标导向ASP的因果约束反事实解释

CoGS: Causality Constrained Counterfactual Explanations using goal-directed ASP

针对机器学习黑盒决策缺乏透明度的问题，提出CoGS框架，借助目标导向ASP系统s(CASP)结合特征因果依赖，从FOLD-SE等规则模型生成符合因果一致性的反事实解释，为用户提供可调整的决策改进路径。

D-BIAS: A Causality-Based Human-in-the-Loop System for Tackling Algorithmic Bias

With the rise of AI, algorithms have become better at learning underlying patterns from the training data including ingrained social biases based on gender, race, etc. Deployment of such algorithms to domains such as hiring, healthcare, law enforcement, etc. has raised serious concerns about fairness, accountability, trust and interpretability in machine learning algorithms. To alleviate this problem, we propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases from tabular datasets. It uses a graphical causal model to repre…

CFGs：使用目标导向ASP的因果约束反事实解释

CFGs: Causality Constrained Counterfactual Explanations using goal-directed ASP

本文提出CFGs框架，利用目标导向ASP系统s(CASP)为基于规则的机器学习模型（如FOLD-SE）自动生成考虑特征因果依赖的反事实解释，通过系列干预实现从初始状态到目标状态的导航。

Expert System Gradient Descent Style Training: Development of a Defensible Artificial Intelligence Technique

Artificial intelligence systems, which are designed with a capability to learn from the data presented to them, are used throughout society. These systems are used to screen loan applicants, make sentencing recommendations for criminal defendants, scan social media posts for disallowed content and more. Because these systems don't assign meaning to their complex learned correlation network, they can learn associations that don't equate to causality, resulting in non-optimal and indefensible decisions being made. In addition to making decisions that are sub-optimal, these systems may create leg…

迈向通用因果推理器

Towards a Universal Causal Reasoner

提出UniCo数据生成框架，覆盖Pearl因果阶梯的18种查询类型，将符号示例转化为代码和自然语言，通过监督微调显著提升LLM的因果推理能力和推理忠实度。

公平性的因果概念及其后果

Causal Conceptions of Fairness and their Consequences

本文将因果公平定义分为约束反事实差异与约束保护特征影响两类，证明并实证其几乎总是产生被强帕累托支配的策略，揭示形式局限与不良后果。