TRUST-AI 2026
European Workshop on Trustworthy AI 2026

Table of Contents

• Preface
  Summary: There were 38 papers submitted for peer-review to this workshop. Out of these, 22 papers were accepted for this volume.

Fairness, Bias and Explainability (Plenary Session 1)

• Fairness-Aware Knowledge Distillation via Symbolic Knowledge Extractors 1-11
  Federico Sabbatini, Roberta Calegari
• Evaluating Trustworthy Multilingual Alignment in LLMs via Synthetic Natural Language Inference 12-23
  Samir Abdaljalil, Erchin Serpedin, Khalid Qaraqe, Hasan Kurban
• Human Rationale Aggregation for Balancing Performance and Explainability in Text Classification 24-30
  Hideki Tsukamoto, Jiyi Li
• Evaluating and Mitigating Gender Bias in Pre-trained Embeddings for ML-based Recruitment 31-41
  Farnaz Faramarzi Lighvan, Lynn Houthuys

Confidence and Hallucination Detection (Plenary Session 2)

• A Voter-Based Stochastic Rejection-Method Framework for Asymptotically Safe Language Model Outputs 42-54
  Jake R. Watts, Joel Sokol
• The First Token Knows: Single-Decode Confidence for Hallucination Detection 55-63
  Mina Gabriel, Pei Wang
• A Trustworthy Federated Framework for Automated Medical Reporting via Two-Stage OCR and NLI-Based Risk Management 64-73
  Yu-Chih Wei, Wei Shan Lin, Chia-Yun Hsu

Risk Assessment, Governance, and Regulation (Plenary Session 3)

• An Empirical Study of Assessing and Mitigating Trustworthiness of Educational AI 74-83
  Evangelia Anagnostopoulou, Nikolaos Antonios Grammatikos, Dimitris Apostolou, Gregoris Mentzas
• Assessment of Trustworthiness of an Industrial AI System using ALTAI – A Feasibility Study 84-92
  Shukun Tokas, Aida Omerovic, Ragnhild Halvorsrud
• Towards a Trustworthy AI Solution for Disinformation Detection 93-103
  Eleni Tsalapati, Giorgos Giotis, Iosif Lazaridis, Thanasis Tsafonis, Christina Vaia, Ilias Kanellos, Cristina Guseth, Teodora Musat
• The EU AI Act Definition of AI System: Interpretive Challenges in Real-World Application and the “Navigating the AI System Definition under the AI Act” (NAIS) Framework 104-117
  María Villalobos Quesada

Robustness, Safety and Security (Plenary Session 4)

• Assessing Calibration and Conformal Coverage of SAR Perception Models under Sim-to-Real Shift 118-132
  Diego Argüello Ron, Christyan Cruz Ulloa, Naresh Ravichandran, Anders Lansner, Pawel Herman, Jaime del Cerro, Oscar García Perales
• Fuzzy Logic Interacts with Attention: Trustworthy Tennis Movements Identification for Motion Capture Data 133-141
  Pawel Powroznik, Maria Skublewska-Paszkowska, Krzysztof Dziedzic, Marcin Barszcz
• DAPHne: A Trust Layer for Adversarial Detection in Histopathology via Gradient–Confidence Monitoring 142-150
  Diogen Babuc

Trustworthy Agents and LLMs (Plenary Session 5)

• S³LoRA: Spectral Sharpness–Guided Pruning for Trustworthy Adaptation of Agentic LLMs 151-163
  Shuang Ao, Shoaib Ehsan, Sarvapali D. Ramchurn
• Trustworthy-by-Design Generative AI Assistants for Industrial Troubleshooting: A Knowledge Graph Grounded Architecture 164-173
  Rohan Jadhav, Emmanuel Papadakis, George Baryannis
• Legitimate Delegation and the Preservation of Human Agency in Trustworthy Agentic AI 174-182
  Alexandru Mateescu
• Do LLMs Explain or Remember? Evaluating Language Model Explanations of Reinforcement Learning Failures 183-192
  Nivetha Suntharamoorthy, Jørn Eirik Betten, Dennis Gross, Eirik Valseth, Helge Spieker

Theoretical and Applied Perspectives (Poster Session)

• Trustworthy AI and Mechanical Expressivism: The Systemic Risk of Ontological Hermeneutical Injustice 193-200
  Marios Thomas Dogkas
• Do not Compare Apples and Offsets: An ESG Alignment Gate for Trustworthy Report Analysis 201-213
  Zexi Wang, Zewen Shen
• Spatial-Temporal Graph Kronecker Convolutional Network with Cauchy Activation Function: Trustworthy Skeleton‑Based Tennis Stroke Recognition Architecture 214-222
  Pawel Powroznik, Maria Skublewska-Paszkowska, Marcin Barszcz, Krzysztof Dziedzic, Sylwester Korga
• Trustworthy Adversarial Robustness via Adaptive Learning-Driven Multi-Teacher Knowledge Distillation 223-233
  Hayat Ullah, Talha Zaidi, Arslan Munir