Vol-4308
urn:nbn:de:0074-4308-x

Copyright © 2026 for the individual papers by the papers' authors. Copyright © 2026 for the volume as a collection by its editors. This volume and its papers are published under the Creative Commons License Attribution 4.0 International (CC BY 4.0).

XAI.it 2026
Explainable AI, Generative and Agentic Systems: Trust, Transparency, and Human Oversight

Proceedings of the 6th Workshop on Explainable AI, Generative and Agentic Systems: Trust, Transparency, and Human Oversight,
co-located with the 24th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2026)

Perugia, Italy, October 6, 2026.

Edited by

Marco Polignano *
Cataldo Musto *
Ernesto William De Luca *
Erasmo Purificato **** ‡
Giovanni Semeraro *

* University of Bari Aldo Moro, Italy
** Otto-von-Guericke University Magdeburg, Germany
*** Leibniz Institute for Educational Media | Georg Eckert Institute, Braunschweig, Germany
**** European Centre for Algorithmic Transparency (ECAT), Joint Research Centre, European Commission
‡ The views expressed in this paper are purely those of the author and may not, under any circumstances, be regarded as an official position of the European Commission.

Table of Contents

Preface
Summary: There were 7 papers submitted for peer-review to this workshop. Out of these, 7 papers were accepted for this volume, 5 as regular papers and 2 as short papers.

Oral Presentations

Explainable Retrieval-Augmented Generation for Multilingual Dark-Pattern Auditing and Digital Consumer Protection 1-14
Jobin Roy, Akshita Sakshi, Shifin Mohammed, Het Darshan Mehta, Marco Polignano, Giovanni Semeraro, Ernesto William De Luca
LLMs as Verbal Translation Layer for TSC Explanations 15-29
Félix Martí-Pérez, Christian Bontveit, Cèsar Ferri, Jan Arne Telle
OCR-Guided Occlusion Sensitivity for Auditing Document Classifiers (Short paper) 30-36
Valerio Caravani, Riccardo De Cesaris, Paolo Merialdo
TRACE-Pave: A Neural Perception and Auditable Decision Framework for Explainable Road Crack Assessment 37-51
Tayyab Rehman, Giovanni De Gasperis
From Post-Hoc Explanations to Assurance-Oriented XAI in Safety-Critical Automatic Target Recognition (Short paper) 52-59
Vanessa Buhrmester, David Muench, Michael Arens
Following Delegation Traces to Study Human Oversight in Interaction with Multimodal AI 60-73
Agnese Chiatti, Matteo Matteucci, Viola Schiaffonati
Explaining Bias-Refusal Geometry Across Languages: An Activation-Steering Study of Llama 2 and GPT-OSS 74-87
Mehuly Chakraborthy, Antonio Rodà

2026-10-05: submitted by Marco Polignano, metadata incl. bibliographic data published under Creative Commons CC0
2026-10-30: published on CEUR Workshop Proceedings (CEUR-WS.org, ISSN 1613-0073) |valid HTML5|