提出对比解释方法，分析两个论点差异的根源。
Contrastive Explanations in Quantitative Bipolar Argumentation Frameworks
- 设计对比归因函数，量化两论点间差异来源
- 基于移除、梯度和沙普利值构建三类解释方法
- 适用于医疗决策与偏见识别场景
论证框架是多种场景下表示与推理信息的有力工具，例如在辅助人工智能模型完成分类任务时，可提供额外可解释性。本文针对定量双极论证框架（QBAFs）引入对比解释，不同于以往仅解释单个论点结果的方法，对比解释旨在揭示两个论点之间的差异成因。我们提出了通用的对比归因函数（CAFs）形式，并确立其应满足的一般性质。进一步地，基于移除、梯度和沙普利值构建了三类具体实现的CAFs，并研究其性质。最后，通过医疗决策与偏见识别案例展示了对比解释的实际效用。
原文摘要 · Abstract (English)
Argumentation frameworks are useful tools for representing and reasoning with information in a variety of settings, e.g. in supplementing AI models as they perform classification tasks, with a notable benefit of providing additional explainability. In this paper, we introduce contrastive explanations for Quantitative Bipolar Argumentation Frameworks (QBAFs), one such formalism. Unlike most existing explanations for QBAFs, which explain the reasoning outcome of a single argument of interest (i.e. a topic argument), contrastive explanations explain the difference between two topic arguments. We introduce a general form of contrastive attribution functions (CAFs) and establish a set of general properties they should satisfy. We introduce CAFs based on removal, gradients and Shapley-values, and study their properties. Finally, to illustrate contrastive explanations, we demonstrate their usefulness in healthcare and bias identification settings.
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。