Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAPJan 1, 2026·Francesco Sovrano· 0 min read URL Cite DOITypeConference paperPublicationProceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, KDD 2026, Jeju Island, Korea, August 9-13, 2026publicationsLast updated on Jan 1, 2026 AuthorsFrancesco SovranoPostdoc← Assessing Model-Agnostic XAI Methods against EU AI Act Explainability Requirements Jan 1, 2026Concept-based Visual Counterfactual Explanations with Diffusion Models Jan 1, 2026 →
