发表机构
Université Paris 8（巴黎第八大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出GFGE通用解释框架，通过五个角色统一归因、替代、反事实等XAI方法，实现解释工作流分析与证据追溯。
AI 中文摘要
可解释人工智能（XAI）涵盖利用不同信息来源并满足不同解释需求的方法。需要一个通用框架来描述这些信息如何成为证据，并作为针对特定接收者的解释进行传达。我们提出了生成解释的通用框架（GFGE），该框架基于解释框架以及“意义解读”和“意义赋予”这两个互补活动。其概念基础是解释/说明模式（IES），该模式将分析者对系统证据的解读、对选定说明的传达以及接收者对该说明的解读联系起来。GFGE通过五个角色使该模式可操作化：数据解释、模型解释、输出解释、可选的事后分析和聚合。角色类型化的操作图记录了方法特定的依赖关系，而证据记录则保留了解释性主张的来源、假设和局限性。解释性问题、受众和上下文指导整个流程。我们针对归因、替代、反事实、概念与原型、内在规则、论证和语言模型方法实例化了GFGE。这些实例化展示了内在、事后和混合工作流如何通过相同的角色来表示，同时保留其独特的证据要求。GFGE为分析解释工作流、将传达的主张追溯至其证据以及识别未解决的解释性依赖提供了共同基础。
英文摘要
Explainable artificial intelligence (XAI) encompasses methods that draw on different sources of information and address different explanatory needs. A common framework is needed to describe how this information becomes evidence and is communicated as an explanation for a particular recipient. We propose the General Framework for Generating Explanations (GFGE), grounded in interpretative frameworks and the complementary activities of \emph{sense-reading} and \emph{sense-giving}. Its conceptual foundation is the Interpret/Explain Schema (IES), which connects an analyst's interpretation of system evidence, the communication of a selected account, and the recipient's interpretation of that account. GFGE operationalises this schema through five roles: data interpretation, model interpretation, output interpretation, optional post-hoc analysis, and aggregation. A role-typed operation graph records method-specific dependencies, while evidence records retain the sources, assumptions, and limitations of explanatory claims. The explanatory question, audience, and context guide the procedure. We instantiate GFGE for attribution, surrogate, counterfactual, concept and prototype, intrinsic rule, argumentation, and language-model methods. These instantiations show how intrinsic, post-hoc, and hybrid workflows can be represented through the same roles while preserving their distinct evidential requirements. GFGE provides a common basis for analysing explanation workflows, tracing communicated claims to their evidence, and identifying unresolved explanatory dependencies.
