跳到正文
arXiv cs.AI· Alexey Ignatiev, Peter J. Stuckey, Joao Marques-Silva·· 4 小时前AI 评分26

形式化反事实解释研究:用合取反事实解释连接最近世界语义与形式化 XAI

On Formal Counterfactual Explanations

AI 导读

论文将最近世界语义下的反事实解释刻画为所有最小距离反例实例的析取范式,并提出合取反事实解释(CFXp)——限定为特征文字合取、保证预测改变的反事实前件子类。研究证明每个 CXp 可为其见证实例诱导一个 AXp,CXp 与见证 AXp 结合可诱导出支持集由该 AXp 精确确定的 CFXp,从而可用现有 AXp/CXp 机制模块化计算 CFXp。

正文 · 原文

View PDF HTML (experimental)

Abstract:Counterfactual explanations are often seen as counterfactual conditionals under closest-world semantics, requiring one to reason over all minimally distant counterexamples. In contrast, formal XAI typically relies on feature-based abductive explanations (AXps) and contrastive explanations (CXps), which admit efficient computation and a minimal hitting-set duality. This paper bridges these perspectives by (i) characterizing closest-world counterfactual explanations explicitly as a disjunctive normal form over all minimally distant counterexample instances, and (ii) introducing conjunctive counterfactual explanations (CFXps), a subclass of counterfactual antecedents restricted to conjunctions of feature literals that guarantee prediction change. The paper establishes structural results connecting CXps, AXps and CFXps: every CXp induces an AXp for its witness instance, and every CXp together with a witness AXp induces a CFXp whose support is precisely determined by that AXp. These theoretical results yield a modular approach for computing CFXps using existing AXp/CXp machinery. Experiments on a representative set of benchmarks using tree ensembles and neural networks show that CFXp extraction is practically efficient. Compared with popular point-based counterfactual explainers, CFXps generally require no more feature changes and can guarantee the counterfactual prediction beyond a single instance.
Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Logic in Computer Science (cs.LO)
Cite as: arXiv:2611.22010 [cs.AI]
  (or arXiv:2611.22010v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.22010

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Alexey Ignatiev [view email]
[v1] Mon, 16 Nov 2026 23:51:26 UTC (1,256 KB)

来源:arXiv cs.AI · arxiv.org