Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives

DOI10.48550/arXiv.2608.11033MaRDI QIDQ7284785arXivFDO

Authors Danilo Danese, Tommaso di Noia, Francesco Musicco, Giuseppe Fasano, Angela Lombardi, Alberto Carlo Maria Mancino

Publication date 11 August 2026

Published in arXiv

Tldr XstrAI: a multi-agent system that structures local explanations as immutable evidence and uses LLMs for audience-aware planning, linguistic realization, and validation to produce narratives tailored to clinicians, patients, or data scientists.

Full work available at URL https://doi.org/10.48550/arXiv.2608.11033

arXiv classification

cs.MA

Cites work

• A Unified Approach to Interpreting Model Predictions
• Computing inter-rater reliability and its variance in the presence of high agreement
• Explanation in artificial intelligence: insights from the social sciences
• MM algorithms for generalized Bradley-Terry models.
• RANK ANALYSIS OF INCOMPLETE BLOCK DESIGNS
• Statistical comparisons of classifiers over multiple data sets

This page was built for publication: Who Are You Explaining To? A Multi-Agent System for Audience-Aware XAI Narratives

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7284785)