发表机构
IMT Atlantique; Sorbonne Université（大西洋国立高等矿业电信学院; 索邦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出DiCEf方法，利用模糊语言词汇整合专家知识，在连续嵌入中生成个性化、可感知且保持成本最小、稀疏和多样的反事实示例。
AI 中文摘要
反事实示例（CFEs）是可解释人工智能（XAI）的基石，通过识别改变模型预测的最小输入修改，提供局部、事后且与模型无关的解释。然而，为了易于理解，这些修改对于被解释者而言也必须具有语义上的意义。本文提出整合以模糊语言词汇表达的知识，以表示被解释者对数据的感知和解释。该模糊词汇所诱导的领域施加了结构约束，使得特征相互依赖，从而阻止了使用基于梯度的优化方法（如DiCE）来生成CFE。本文在此语言领域中提出了一种连续数据嵌入，并利用它定义了一种DiCE的变体，允许对被解释者进行个性化，命名为DiCEf。正如在真实世界数据集上的实验结果所示，DiCE方法的这一扩展能够生成在语言上可感知的CFEs，同时保持成本最小性、稀疏性和多样性。
英文摘要
CounterFactual Examples (CFEs) are a cornerstone of eXplainable Artificial Intelligence (XAI), offering local, post hoc, and model-agnostic explanations by identifying minimal input modifications that alter a model's prediction. Yet, in order to be intelligible, these modifications must also be semantically meaningful to the explainee. This paper proposes to integrate knowledge expressed as a fuzzy linguistic vocabulary to represent the explainee's perception and interpretation of the data. The domain induced by this fuzzy vocabulary imposes structural constraints that make the features dependent, preventing the use of gradient-based optimisation methods for CFE generation, e.g., DiCE. The paper proposes a continuous data embedding in this linguistic domain and exploits it to define a variant of DiCE that allows personalisation for the explainee, named DiCEf. As illustrated by experimental results on a real-world dataset, this extension of the DiCE method enables the generation of CFEs that are linguistically perceptible while preserving cost minimality, sparsity, and diversity.
Journal refThe 17th International Conference on Scalable Uncertainty Management (SUM 2026), Oct 2026, Athens, Greece
