让解释能指导实际决策，才是可落地的可解释性。
Interpretability Can Be Actionable
- 以能否促成具体行动作为评价标准，而非仅停留在解释层面。
- 提出可操作性可解释性的双维度框架：具体性与验证性。
- 适合关注模型落地、决策支持的研究者与工程师。
可解释性旨在阐明深度神经网络的行为。尽管发展迅速，但越来越多的担忧是，大部分工作未能转化为实际影响，引发了对其相关性和实用性的质疑。本文认为，核心缺失并非新方法，而是评估标准：可解释性应以‘可操作性’衡量——即洞察力能否在解释研究之外促成具体决策和干预。我们从具体性和验证性两个维度定义可操作性可解释性，并分析阻碍其实现的障碍。为应对这些挑战，我们识别了五个可解释性具有独特优势的应用领域，并提出一个与实际成果对齐的评估框架。目标不是削弱探索性研究，而是将可操作性确立为可解释性研究的核心目标。
原文摘要 · Abstract (English)
Interpretability aims to explain the behavior of deep neural networks. Despite rapid growth, there is mounting concern that much of this work has not translated into practical impact, raising questions about its relevance and utility. This position paper argues that the central missing ingredient is not new methods, but evaluation criteria: interpretability should be evaluated by actionability--the extent to which insights enable concrete decisions and interventions beyond interpretability research itself. We define actionable interpretability along two dimensions--concreteness and validation--and analyze the barriers currently preventing real-world impact. To address these barriers, we identify five domains where interpretability offers unique leverage and present a framework for actionable interpretability with evaluation criteria aligned with practical outcomes. Our goal is not to downplay exploratory research, but to establish actionability as a core objective of interpretability research.
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。