Reasons, Values, Stakeholders: A Philosophical Framework for Explainable Artificial Intelligence
Atoosa Kasirzadeh University of Toronto (Toronto, Canada)、Australian National University (Canberra, Australia)
Abstract
The societal and ethical implications of the use of opaque artificial intelligence systems for consequential decisions, such as welfare allocation and criminal justice, have generated a lively debate among multiple stakeholder groups, including computer scientists, ethicists, social scientists, policy makers, and end users. However, the lack of a common language or a multi-dimensional framework to appropriately bridge the technical, epistemic, and normative aspects of this debate prevents the discussion from being as productive as it could be. Drawing on the philosophical literature on the nature and value of explanations, this paper offers a multi-faceted framework that brings more conceptual precision to the present debate by (1) identifying the types of explanations that are most pertinent to artificial intelligence predictions, (2) recognizing the relevance and importance of social and ethical values for the evaluation of these explanations, and (3) demonstrating the importance of these explanations for incorporating a diversified approach to improving the design of truthful algorithmic ecosystems. The proposed philosophical framework thus lays the groundwork for establishing a
中文速览
人工智能系统在招聘、信贷、医疗、司法等高风险场景中大量应用，但这些系统往往像"黑箱"一样不透明，让人无法理解它为何做出某个决定——这正是可解释人工智能（explainable AI）研究要破解的核心难题。现有技术方案虽然已能从特征重要性、因果关系、反事实推断等角度给出局部解释，却缺乏一套能同时容纳技术、伦理与社会多个维度的统一框架。为此，本文从哲学文献出发，提出了一个以"理由—价值—利益相关者"（Reasons-Values-Stakeholders，RVS）为三条轴线的多层次框架：它不仅涵盖数据分析层面的特征解释，还纳入了涉及数据表示、数学结构与优化目标的"设计解释"，并明确要求把社会公正、问责制、反歧视等规范性价值纳入对解释质量的评价之中。这一框架的重要性在于，它为技术人员、伦理学家、政策制定者和受影响的普通用户搭建了共同对话的平台，有助于推动算法决策系统走向真正意义上的民主化与可信赖化。
原文 arXiv:2103.00752;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2103.00752v1