用逻辑框架回答‘为什么是这个而不是那个’，精准对比不同结果的原因。
Why this and not that? A Logic-based Framework for Contrastive Explanations
- 基于命题逻辑构建对比解释的统一框架
- 能找出导致不同结果的最小原因集合
- 适合需要可解释决策的AI系统开发者
我们定义了几类与对比解释相关的典型问题，每个问题都回答'为什么P但不是Q？'的形式。这些问题会分别计算P和Q的成因，并明确比较其差异。我们在命题逻辑设定下研究了这些定义的基本性质，发现该框架能够捕捉文献中已有的最小基数型对比解释。此外，我们对这些问题的计算复杂性进行了深入分析。还利用答案集编程（ASP）实现了针对合取范式（CNF）公式的求解，并通过多个实例展示了其实际应用效果。
原文摘要 · Abstract (English)
We define several canonical problems related to contrastive explanations, each answering a question of the form ''Why P but not Q?''. The problems compute causes for both P and Q, explicitly comparing their differences. We investigate the basic properties of our definitions in the setting of propositional logic. We show, inter alia, that our framework captures a cardinality-minimal version of existing contrastive explanations in the literature. Furthermore, we provide an extensive analysis of the computational complexities of the problems. We also implement the problems for CNF-formulas using answer set programming and present several examples demonstrating how they work in practice.
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。