Skip to main content
SpringerLink
Log in

Explainable and Transparent AI and Multi-Agent Systems

5th International Workshop, EXTRAAMAS 2023, London, UK, May 29, 2023, Revised Selected Papers

  • Conference proceedings
  • © 2023

Overview

Editors:
  1. Davide Calvaresi

    1. University of Applied Sciences and Arts Western Switzerland, Sierre, Switzerland

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  2. Amro Najjar

    1. Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  3. Andrea Omicini

    1. Alma Mater Studiorum, Università di Bologna, Bologna, Italy

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  4. Reyhan Aydogan

    1. Ozyegin University, Istanbul, Türkiye

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  5. Rachele Carli

    1. Alma Mater Studiorum, Università di Bologna, Bologna, Italy

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  6. Giovanni Ciatto

    1. Alma Mater Studiorum, Università di Bologna, Bologna, Italy

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  7. Yazan Mualla

    1. Université de Technologie de Belfort-Montbéliard, Belfort Cedex, France

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

  8. Kary Främling

    1. Umeå University, Umeå, Sweden

    View editor publications

    You can also search for this editor in PubMed   Google Scholar

Part of the book series: Lecture Notes in Computer Science (LNCS, volume 14127)

Part of the book sub series: Lecture Notes in Artificial Intelligence (LNAI)

Included in the following conference series:

Conference proceedings info: EXTRAAMAS 2023.

This is a preview of subscription content, log in via an institution to check access.

Access this book

Log in via an institution
eBook USD 49.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 64.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Other ways to access

Licence this eBook for your library

Institutional subscriptions

About this book

This volume LNCS 14127 constitutes the refereed proceedings of the 5th International Workshop, EXTRAAMAS 2023, held in London, UK, in May 2023.  

The 15 full papers presented together with 1 short paper were carefully reviewed and selected from 26 submissions. The workshop focuses on Explainable Agents and multi-agent systems; Explainable Machine Learning; and Cross-domain applied XAI.

 


Keywords

Table of contents (16 papers)

  1. Front Matter

    Pages i-xii
    Download chapter PDF

  2. Explainable Agents and Multi-Agent Systems

    1. Front Matter

      Pages 1-1
      Download chapter PDF

    2. Mining and Validating Belief-Based Agent Explanations

      • Ahmad Alelaimat, Aditya Ghose, Hoa Khanh Dam
      Pages 3-17

    3. Evaluating a Mechanism for Explaining BDI Agent Behaviour

      • Michael Winikoff, Galina Sidorenko
      Pages 18-37

    4. A General-Purpose Protocol for Multi-agent Based Explanations

      • Giovanni Ciatto, Matteo Magnini, Berk Buzcu, Reyhan Aydoğan, Andrea Omicini
      Pages 38-58

    5. Dialogue Explanations for Rule-Based AI Systems

      • Yifan Xu, Joe Collenette, Louise Dennis, Clare Dixon
      Pages 59-77

    6. Estimating Causal Responsibility for Explaining Autonomous Behavior

      • Saaduddin Mahmud, Samer B. Nashed, Claudia V. Goldman, Shlomo Zilberstein
      Pages 78-94

  3. Explainable Machine Learning

    1. Front Matter

      Pages 95-95
      Download chapter PDF

    2. The Quarrel of Local Post-hoc Explainers for Moral Values Classification in Natural Language Processing

      • Andrea Agiollo, Luciano Cavalcante Siebert, Pradeep Kumar Murukannaiah, Andrea Omicini
      Pages 97-115

    3. Bottom-Up and Top-Down Workflows for Hypercube- And Clustering-Based Knowledge Extractors

      • Federico Sabbatini, Roberta Calegari
      Pages 116-129

    4. Imperative Action Masking for Safe Exploration in Reinforcement Learning

      • Sumanta Dey, Sharat Bhat, Pallab Dasgupta, Soumyajit Dey
      Pages 130-142

    5. Reinforcement Learning in Cyclic Environmental Changes for Agents in Non-Communicative Environments: A Theoretical Approach

      • Fumito Uwano, Keiki Takadama
      Pages 143-159

    6. Inherently Interpretable Deep Reinforcement Learning Through Online Mimicking

      • Andreas Kontogiannis, George A. Vouros
      Pages 160-179

    7. Counterfactual, Contrastive, and Hierarchical Explanations with Contextual Importance and Utility

      • Kary Främling
      Pages 180-184

  4. Cross-Domain Applied XAI

    1. Front Matter

      Pages 185-185
      Download chapter PDF

    2. Explanation Generation via Decompositional Rules Extraction for Head and Neck Cancer Classification

      • Victor Contreras, Andrea Bagante, Niccolò Marini, Michael Schumacher, Vincent Andrearczyk, Davide Calvaresi
      Pages 187-211

    3. Metrics for Evaluating Explainable Recommender Systems

      • Joris Hulstijn, Igor Tchappi, Amro Najjar, Reyhan Aydoğan
      Pages 212-230

    4. Leveraging Imperfect Explanations for Plan Recognition Problems

      • Ahmad Alelaimat, Aditya Ghose, Hoa Khanh Dam
      Pages 231-248

    5. Reinterpreting Vulnerability to Tackle Deception in Principles-Based XAI for Human-Computer Interaction

      • Rachele Carli, Davide Calvaresi
      Pages 249-269

    6. Enhancing Wearable Technologies for Dementia Care: A Cognitive Architecture Approach

      • Matija Franklin, David Lagnado, Chulhong Min, Akhil Mathur, Fahim Kawsar
      Pages 270-280
Back to top

Other volumes

  1. Explainable and Transparent AI and Multi-Agent Systems

Editors and Affiliations

  • University of Applied Sciences and Arts Western Switzerland, Sierre, Switzerland

    Davide Calvaresi

  • Luxembourg Institute of Science and Technology, Esch-sur-Alzette, Luxembourg

    Amro Najjar

  • Alma Mater Studiorum, Università di Bologna, Bologna, Italy

    Andrea Omicini, Rachele Carli, Giovanni Ciatto

  • Ozyegin University, Istanbul, Türkiye

    Reyhan Aydogan

  • Université de Technologie de Belfort-Montbéliard, Belfort Cedex, France

    Yazan Mualla

  • Umeå University, Umeå, Sweden

    Kary Främling

Bibliographic Information

Publish with us

Policies and ethics

Back to top

Search

Navigation