Can Global XAI Methods Reveal Injected Bias in LLMs? SHAP vs Rule Extraction vs RuleSHAPMay 1, 2025·Francesco Sovrano· 0 min read URL Cite DOITypeJournal articlePublicationCoRRpublicationsLast updated on May 1, 2025 AuthorsFrancesco SovranoPostdoc← Beyond the lab: An in-depth analysis of real-world practices in government-to-citizen software user documentation May 1, 2025On the interplay of Explainability, Privacy and Predictive Performance with Explanation-assisted Model Extraction May 1, 2025 →