LB/D/DC@xAI 2026
xAI-2026 Late-breaking Work, Demos and Doctoral Consortium Joint Proceedings

Table of Contents

• Preface
  Maria Riveiro, Caroline Petitjean, Tuwe Löfström-Cavallin, Javier Del Ser, Andreas Holzinger, Luca Longo

Late-breaking work

• Counterfactual Explanations for Incomplete Inputs Using Flow-Based Generative Models 1-8
  Francesco Leofante, Daniel Neider, Mustafa Yalçıner
• Concept-based Explanations of Segmentation and Detection models in Natural Disaster Management 9-16
  Samar Heydari, Jawher Said, Galip Ümit Yolcu, Evgenii Kortukov, Elena Golimblevskaia, Evgenios Vlachos, Vasileios Mygdalis, Ioannis Pitas, Sebastian Lapuschkin, Leila Arras
• Interpretability-Informed Curriculum Learning for Blind Estimation of Room Acoustic Parameters with a Vision Transformer 17-24
  Luis Paulo Albuquerque Guedes, Mariane Rembold Petraglia, Julio Cesar Boscher Torres
• NS-AIME: Rule-Guided Re-Constraint of Approximate Inverse Explanations 25-32
  Takafumi Nakanishi
• CAX-Gate: a Context-Aware Explainability Fusion Architecture for Dynamical Adjustment of LIME-to-SHAP Attributions Ratio with Application in Colonoscopy 33-40
  Pınar Karadayı Ataş, Luca Longo
• ConceptTracer: Interactive Analysis of Concept Saliency and Selectivity in Neural Representations 41-48
  Ricardo Knauer, Andre Beinrucker, Erik Rodner
• Exploring the Accuracy-size Trade-off in Extended Argumentative Decision Graphs Using SHAP or LIME Feature Selection 49-56
  Lucas Rizzo, Luca Longo
• SAFE AI platform: A Platform for Continuous Evaluation of Accuracy, Fairness, Explainability and Robustness in Machine Learning Systems 57-64
  Golnoosh Babaei, Marco Brandirali, Paolo Giudici
• Investigating Inductive Bias in LLMs - A Case Study in Creditworthiness Assessment 65-72
  Thi Hoang Anh Tran, Emiel Caron, Hans Weigand
• Building Trust in PINNs: Error Estimation Through Finite Difference Methods 73-80
  Aleksander Krasowski, René P. Klausen, Aycan Celik, Sebastian Lapuschkin, Wojciech Samek, Jonas Naujoks
• When One Agent Reshapes Another: Cross-Hessian Interpretation of Local Coupling in MARL 81-88
  Risal Shahriar Shefin, Debashis Gupta, Murtadha Alsayegh, Sarra Alqahtani
• Interpretable EEG Microstate Discovery via Variational Deep Embedding: A Systematic Architecture Search with Multi-Quadrant Evaluation 89-96
  Saheed Faremi, Andrea Visentin, Luca Longo
• Delayed Convergence and Emergent CoT Reliance in RL-Tuned Language Models 97-104
  Pablo Pérez-Lázaro, Rocío Aznar-Gimeno, Francisco José Lacueva-Pérez, Paula Peña-Larena, Rafael del-Hoyo-Alonso
• Calibrating Clinician Trust in Explainable AI Summarization for Obstetrics: A Sociotechnical Design Study of the MedGPT Portugal Use Case 105-112
  Filipe Bernardi, Daniel Rodrigues, Rute Almeida, Vinicius Lima, Isabela Guerche, Julio Souza, Ricardo Correia, Luis Conceicao, Goreti Marreiros, Alberto Freitas
• Evaluating Logic Learning Machine model with SAFE-AI Metrics 113-120
  Vasily Kolesnikov, Damiano Verda, Nicolò Pinna, Danilo Franco, Paolo Giudici
• ISAAC: Intervention-Based Structural Auditing of Deep Models for Transcription Factor Binding 121-128
  Barbara Tarantino, Paolo Giudici
• Multi-metric Evaluation of the Statistical Radiomic Feature Attribution Mapping method for Explainable Radiomic Models 129-136
  Oleksandr Davydko, Vladimir Pavlov, Luca Longo
• Quantifying Cross-Modal Interactions in Multimodal Glioma Survival Prediction via InterSHAP: Evidence for Additive Signal Integration 137-144
  Iain Swift, Jing Hua Ye, Ruairí O’Reilly
• AGOP as Explanation: From Feature Learning to Per-Sample Attribution in Image Classifiers 145-152
  Raj Kiran Gupta Katakam
• A Patch-Masking Approach to Explain CNNs and Vision Transformers through Class-Specific Impacts 153-160
  Jean-Marc Boutay, Damian Boquete, Deniz Köprülü, Ludovic Pfeiffer, Guido Bologna
• Explainable Emotion Recognition with EEG Wearable Devices 161-168
  Tommaso Colafiglio, Angela Lombardi, Paolo Sorino, Domenico Lofù, Tommaso Di Noia
• Explanation-Driven Carousels for Two-Dimensional Recommendation Interfaces 169-176
  André Levi Zanon, Derek Bridge
• Explaining Process Control Optimisation Recommendations via GradientSHAP and Implicit Differentiation 177-184
  Paul Darm, Cem Alpturk, Kenneth Ulrich, William Duncan, Ali Anwar, Annalisa Riccardi

Demos

• Explainable AI for Operational SpaceWeather Forecasting: An Interpretable Prototype for the EMBRACE-INPE Monitoring Network 185-192
  Reinaldo R. Rosa, Andressa Ferreira, Salatiel Jordão, Carlos E. Falandes, Mariana Rubet, André R.F. Martinon, Stephan Stephany, Francisco C. R. Fernandes, Juan A. Valdivia
• Calibrated Explanations:Trustworthy Uncertainty for Every Prediction and Explanation 193-200
  Helena Löfström, Tuwe Löfström,
• XTab-CDS: A Lightweight Framework for Explainable Clinical Decision Support on Tabular Data 201-208
  Adelia Manafov, Artem Mozharov, Khawla Elhadri, Ramona Simon, Jan Gohe, Max Blümer, Ben Williges, Jörg Schlötterer, Diana Arweiler-Harbeck, Benedikt Höing, Christin Seifert
• GPUTextSHAP: a GPU-Accelerated Permutation SHAP for Textual Data 209-216
  Henrique Margotte, Bruno H. Meyer, Carmem S. Hara, Aurora T. R. Pozo, Wagner M. Nunan Zola
• Grounding LLM Explanations for Process Mining via Agentic Function Calling 217-224
  Oleksii Kalashnikov, Jonas Amling, Christian Dormagen, Andreas Fischer, Stephan Scheele, Ute Schmid
• Suppressive Dropout: A Demonstration of Explainable Channel-Selective Regularization for Preserving Rare Features 225-232
  Seunghyun Lee

Doctoral Consortium

• User Arousal in XAI Usage 233-240
  Maurice L. Pape
• Human-Centred Explainable Conversational AI: Explainability, Persona Adaptation, and Entrepreneurial Agency 241-248
  Kudzai Sauka
• An Approach to Selecting the Best Explainability Method for CNNs Based on Distance Metrics and Human Perception 249-256
  Daniel da Silva Costa
• Progressive and Interpretable Explanations for Machine Learning Models on Spectroscopy Data 257-264
  Mingxing Zhang
• A Comprehensive Investigation of the Impact of Locality on the Explainability of Automatic Text Classification 265-272
  Liziane Santos Soares
• Explainable Disentangled Representation Learning of Recurring Brain Activation Patterns via Variational Autoencoders 273-280
  Saheed Faremi
• From Recommendation to Deliberation: Explainable AI for Judicial Decision Support in Brazil 281-288
  Eduardo Caruso Barbosa Pacheco
• Designing and Evaluating Calibration-Driven Recommender Systems for Fairness and Explainability 289-296
  Paul Atauchi
• Multi-Agent Evaluation of XAI for Human-AI Trust and Cooperative Adaptation 297-304
  Francesco Musicco
• Condensed Dataset Representations via Latent Prototypical Features 305-312
  Korbinian Franz Rudolf
• Towards Structural Explainability for Reliable and Governable Large Language Models 313-320
  Marco Aspromonte
• Explainability-Guided Active Data Acquisition for Classification 321-328
  Cristian Pessatti dos Anjos