LB/D/DC@xAI 2025
xAI-2025 Late-breaking Work, Demos and Doctoral Consortium Joint Proceedings

Table of Contents

• Preface
  Przemysław Biecek , Slawomir Nowaczyk , Gitta Kutyniok , Luca Longo

Late-Breaking Work

• On the Interplay of Explainability, Privacy and Predictive Performance with Explanation-assisted Model Extraction 1-8
  Fatima Ezzeddine, Rinad Akel, Ihab Sbeity, Silvia Giordano, Marc Langheinrich, Omran Ayoub

• SHAP-Guided Regularization in Machine Learning Models 9-16
  Amal Saadallah

• Dialogue-based XAI for Predictive Policing: a Field Study 17-24
  Fabian Beer, Dimitry Mindlin, Sebastian Kost, Isabel Krause, Katharina Schwarz, Kai Seidensticker, Philipp Cimiano, Elena Esposito

• Explaining Process Behavior: A Declarative Framework for Interpretable Event Data 25-32
  Christian Dormagen, Jonas Amling, Stephan Scheele, Ute Schmid

• This Part Looks Alike This: Tdentifying Important Parts of Explained Instances and Prototypes 33-40
  Jacek Karolczak, Jerzy Stefanowski

• Robustness Analysis of Counterfactual Explanations from Generative Models: An Empirical Study 41-48
  Kseniya Sahatova, Johannes De Smedt, Xuefei Lu

• Integrated Gradients for Enhanced Interpretation of P3b-ERP Classifiers Trained with EEG-superlets in Traditional and Virtual Environments 49-56
  Vladimir Marochko, Jacek Rogala, Luca Longo

• Concept Bottleneck Model with Emergent Communication Framework for Explainable AI 57-64
  Farnoosh Javar, Kei Wakabayashi

• Explainable Evaluation of Emotion Recognition with Low-Cost EEG: Feature Engineering and Interpretability Insights 65-72
  Tommaso Colafiglio, Angela Lombardi, Paolo Sorino, Domenico Lofù, Danilo Danese, Fedelucio Narducci, Eugenio Di Sciascio, Tommaso Di Noia

• Assessing Reliability of Explanations in Unbalanced Datasets: a Use-case on the Occurrence of Frost Events 73-80
  Ilaria Vascotto, Valentina Blasone, Alex Rodriguez, Alessandro Bonaita, Luca Bortolussi

• Explainability in Generative AI: An Umbrella Review of Current Techniques, Limitations, and Future Directions 81-88
  Prabha M. Kumarage, Mirka Saarela

• Learning Interpretable Rules from Neural Networks: Neurosymbolic AI for Radar Hand Gesture Recognition 89-96
  Sarah Seifi, Tobias Sukianto, Cecilia Carbonelli, Lorenzo Servadei, Robert Wille

• Interpretable Deepfake Voice Detection: A Hybrid Deep-Learning Model and Explanation Evaluation 97-104
  Jacob LaRock, Md Shajalal, Gunnar Stevens

• PsyLingXAV: A Psycholinguistics Design Framework for XAI in Automated Vehicles 105-112
  Ashkan Y. Zadeh, Xiaomeng Li, Andry Rakotonirainy, Ronald Schroeter, Sebastien Glaser

• Beyond One-Size-Fits-All: How User Objectives Shape Counterfactual Explanations 113-120
  Orfeas Menis Mastromichalakis, Jason Liartis, Giorgos Stamou

• A Study on the Faithfulness of Feature Attribution Explanations in Pruned Vision-Based Multi-Task Learning 121-128
  Xenia Demetriou, Sophie Sananikone, Vojislav Tobias Westmoreland, Matthia Sabatelli, Marco Zullich

• Enhancing Cost-Sensitive Tree-Based XAI Surrogate Method: Exploring Alternative Cost Matrix Formulation 129-136
  Marija Kopanja, Miloš Savić, Luca Longo

• PFLex: Perturbation-Free Local Explanations in Language Model-Based Text Classification 137-144
  Yogachandran Rahulamathavan, Misbah Farooq, Varuna De Silva

• Visual Analysis of Action Policy Behavior: A Case Study in Grid-World Driving 145-152
  Timo P. Gros, David Groß, Julius Kamp, Stefan Gumhold, Jörg Hoffmann

• Interpretable Sexism Detection with Explainable Transformers 153-160
  Shamima Rayhana, Md Shajalal, Md Atabuzzaman, Gunnar Stevens

• Explaining in Natural Language: A Discussion on Leveraging the Reasoning Capabilities of LLMs for XAI 161-168
  Arthur Picard, Yazan Mualla, Franck Gechter

• Bridging Structural and Functional Imaging: Integrated PET/CT Radiomics with Explainable Machine Learning 169-176
  Pierfrancesco Novielli, Donato Romano, Michele Magarelli, Pierpaolo Di Bitonto, Roberto Bellotti, Sabina Tangaro

• Concepts Guide and Explain Diffusion Visual Counterfactuals 177-184
  Franz Motzkus, Ute Schmid

• Here Comes the Explanation: A Shapley Perspective on Multi-contrast Medical Image Segmentation 185-192
  Tianyi Ren, Juampablo Heras Rivera, Hitender Oswal, Yutong Pan, Agamdeep Chopra, Jacob Ruzevick, Mehmet Kurt

• MetaCoXAI Framework: Linking XAI, Computational Thinking, and Metacognition for Learning 193-200
  Gi Woong Choi, Sang Won Bae

• Global Interpretability for ProtoPNet Using Rule-Based Explanations 201-208
  Alec Parise, Brian Mac Namee

• SignalGrad-CAM: Beyond Image Explanation 209-216
  Samuele Pe, Tommaso Buonocore, Giovanna Nicora, Enea Parimbelli

• Discriminative Feature Analysis in XAI for Multi-Class Classification of Oral Lesions 217-224
  Paolo Fantozzi, Paolo Junior Fantozzi, Najwa Yousef, Mathilde Casagrande, Gianluca Tenore, Antonella Polimeni, James J. Sciubba, Tiffany Tavares, Umberto Romeo, Ahmed Sultan, Maurizio Naldi

• Investigating the Relationship Between Debiasing and Artifact Removal using Saliency Maps 225-232
  Lukasz Sztukiewicz, Ignacy Stępka, Michał Wiliński, Jerzy Stefanowski

• Multi-Level Explainability in Radiomic-based Classification of Multiple Sclerosis and Ischemic Lesions 233-240
  Nighat Bibi, Kathleen M. Curran, Ronan P. Killeen, Jane Courtney

• Do the Explanations Make Sense? Explainable Fake Review Identification and Users’ Perspectives on Explanations 241-248
  Md Shajalal, Md Atabuzzaman, Alexander Boden, Gunnar Stevens, Delong Du

• Bridging the Sim-to-Real Gap with Explainability for ML-based Object Detection on Sonar Data 249-256
  Şakir Furkan Yöndem, Ramin Tavakoli Kolagari, Benedikt Schlereth-Groh

Demos

• A GUI for the Fair & Explainable Selective Classifier IFAC 257-264
  Daphne Lenders, Roberto Pellungrini, Fosca Giannotti

• Explanation Groves – Controlling the Trade-off between the Degree of Explanation vs. its Complexity 265-272
  Gero Szepannek

• Deriving and Visualizing Predictive Rules for Disease Risk: A Transparent Approach to Medical AI 273-280
  Enrico Sciacca, Giorgia Grasso, Damiano Verda, Enrico Ferrari

• EvalxNLP: A Framework for Benchmarking Post-Hoc Explainability Methods on NLP Models 281-288
  Mahdi Dhaini, Kafaite Zahra Hussain, Efstratios Zaradoukas, Gjergji Kasneci

• IPEXCO: A Platform for Iterative Planning with Interactive Goal-Conflict Explanations 289-296
  Rebecca Eifler, Guilhem Fouilhé

• ClustXRAI: Interactive Cluster Exploration and Explanation for Process Mining with Generative AI 297-304
  Christopher Lorenz Werner, Jonas Amling, Christian Dormagen, Stephan Scheele

• SkinSplain: An XAI Framework for Trust Calibration in Skin Lesion Analysis 305-312
  Tim Katzke, Mustafa Yalçıner, Jan Corazza, Alfio Ventura, Tim-Moritz Bündert, Emmanuel Müller

Doctoral Consortium

• Extended Nomological Deductive Reasoning (eNDR) for Transparent AI Outputs 313-320
  Gedeon Hakizimana

• A Novel Approach for Benchmarking Local Binary Classification XAI Methods Using Synthetic Ground Truth Datasets 321-328
  Karim Moustafa

• Explaining Time Series Classifiers Through Post-Hoc XAI Methods Capturing Temporal Dependencies 329-336
  Ephrem T. Mekonnen

• Uncertainty Considerations of Explainable AI in Data-Driven Systems 337-344
  Fatima Rabia Yapicioglu

• Explainable Virtual Metrology in Semiconductor Industry 345-352
  Amina Mević

• Towards Ensemble Explanation Strategies and Solving the Disagreement Problem in XAI 353-360
  Craig Pirie

• Beyond Model Trust: Dual XAI for Adaptive and User-Centric Explainability 361-368
  Maria Luigia Natalia De Bonis

• Explaining Uncertainty: Exploring the Synergies of Explainable Artificial Intelligence and Uncertainty Quantification 369-376
  Emily Schiller

• Interpretable Neural System Dynamics: Combining Deep Learning with System Dynamics Modeling to Support Critical Applications 377-384
  Riccardo D’Elia

• How to Explain in XAI? - Investigating Explanation Protocols in Decision Support Systems 385-392
  Caterina Fregosi

• Towards Explainable Image Classification 393-400
  Vahidin Hasić

• Temporal Explainable AI Models for Surgery Evaluation 401-408
  Haadia Amjad

• Human-Centered Explainable AI: Creating Explanations that Address Stakeholder Needs 409-416
  Anton Hummel

• Strengthening of the Italian Research Infrastructure for Metrology and Open Access Data in support to the Agrifood (METROFOOD-IT) 417-424
  Michele Magarelli