发表机构
Johannes Gutenberg University Mainz; University of Tampere（美因茨约翰内斯·古腾堡大学; 坦佩雷大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文探讨反事实解释（CEs）在AI模型部署中用于正当性与算法求助的规范正当性，发现其会忽略ML流程中组织的关键选择，无法充分回答重要的“为什么”问题，凸显需考虑此类选择。
AI 中文摘要
反事实解释（Counterfactual Explanations, CEs）在可解释人工智能（AI）中被广泛应用，用于展示若输入特征被操纵，模型的输出会如何变化。该技术被用于模型调试、预测解释、决策正当性论证及提供算法求助等一系列任务。本文探讨在现实模型部署场景中采用反事实解释的规范正当性，讨论CEs常见应用目的涉及的不同利益相关方，发现正当性与算法求助对CEs有更严格要求。尤其，我们发现将CEs直接用于正当性论证与算法求助，会忽略机器学习（ML）流程中存在争议的选择，从而模糊了决策及对应反事实解释也是组织物化设计与治理选择的产物这一事实。我们通过四个针对ML流程中“上游”干预的实证实验验证这一点，证明这些干预会影响生成的反事实解释。我们发现，组织对特征与标签测量模型、业务需求、模型验证及模型成功指标的选择，对反事实解释的影响与生成方法的细节相当甚至更大。我们的发现强调在提供正当性与算法求助时需考虑此类选择，有力提醒人们这些任务的关系属性。作为假定的正当性或求助建议，CEs无法为一些重要的“为什么”问题提供充分答案，因为它们排除了对决策者是否应采取不同行动的考量。
英文摘要
Counterfactual explanations (CEs) are widely used in explainable artificial intelligence (AI) to show how a model's outputs would change if the input features were manipulated. This technique is used for a range of tasks such as debugging models, explaining predictions, justifying decisions, and providing algorithmic recourse. In this paper, we explore the normative legitimacy of employing counterfactuals in real-life model deployment settings. We discuss the different stakes involved in these different purposes for which CEs are commonly employed, and find stricter requirements for justification and recourse. In particular, we find that naive application of CEs for justification and recourse can lead to ignoring contestable choices made throughout the machine learning (ML) pipeline, thus obfuscating that decisions and counterfactuals for those decisions are also artifacts of an organization's materialized design and governance choices. We demonstrate this with four empirical experiments involving interventions at stages of the ML pipeline ``upstream" of the explanation itself, and show that these affect the generated counterfactuals. We find that an organization's choices on measurement models for feature and labels, business requirements, model validation, and the metric of model success have as much or more impact on the generated counterfactuals as the specifics of the generating method. Our findings underline the need to account for such choices upon providing justification and recourse, providing a stark reminder of the relational nature of these tasks. As putative justifications or recourse recommendations, CEs do not provide adequate answers to some important "why"-questions because they preclude consideration of whether the decision-maker ought to have acted differently.
