Fifth Workshop on XCBR:
Case-Based Reasoning for the Explanation of Intelligent Systems


XCBR is a workshop aiming to provide a medium of exchange for information about trends, research issues and practical experiences in the use of Case-Based Reasoning (CBR) methods for the inclusion of explanations to several AI techniques (including CBR itself).

The success of intelligent systems has led to an explosion of the generation of new autonomous systems with new capabilities like perception, reasoning, decision support and self-action. Despite the tremendous benefits of these systems, they work as black-box systems and their effectiveness is limited by their inability to explain their decisions and actions to human users. The problem of explain-ability in Artificial Intelligence is not new but the rise of the autonomous intelligent systems has created the necessity to understand how these intelligent systems achieve a solution, make a prediction or a recommendation or reason to support a decision in order to increase users’ trust in these systems. Additionally, the European Union included in their regulation about the protection of natural persons with regard to the processing of personal data a new directive about the need of explanations to ensure fair and transparent processing in automated decision-making systems.

The goal of Explainable Artificial Intelligence (XAI) is “to create a suite of new or modified machine learning techniques that produce explainable models that, when combined with effective explanation techniques, enable end users to understand, appropriately trust, and effectively manage the emerging generation of Artificial Intelligence (AI) systems”.

For this purpose, the XCBR workshop is intended to have a structure of activities that helps an exchange of ideas and interaction, suited to highlight the main bottlenecks and challenges, as well as the more promising research lines, for CBR research related to the explanation of intelligent systems.

CBR systems have previous experiences in interactive explanations and in exploiting memory-based techniques to generate these explanations that can be successfully applied to the explanation of emerging AI and machine learning techniques.


Research contributions submitted to the workshop will be related to areas that include, but are not limited to, the following:

  • AI explanation methods using CBR: CBR explanations of ML techniques, planning, recommender systems, decision-making techniques.
  • CBR for explaining data obtained from sensor systems, Internet of Things, or wearables.
  • Explanations of complex CBR systems.
  • Hybrid CBR models to provide explanation capabilities.
  • Case-based explanation capabilities for different domains.
  • Lessons learned in XCBR investigations.
  • Challenge tasks for XCBR systems in novel AI techniques.
  • Measures and methods of evaluation for assessing case-based explanations.
  • User interaction for explanations.
  • The role of experience on explain-ability.


We invite submissions of two types:

  • Long research and application papers: a maximum of 12 pages describing original contributions.
  • Short position papers: a maximum of 6 pages describing new research ideas and partially developed frameworks

Papers must be submitted in electronic form as PDF. Springer LNCS is the format required for the final camera-ready copy. The accepted papers will be included in CEUR-WS proceedings and submissions are invited to use the LaTeX template files at CEUR-WS ICCBR XCBR 2023 (click) . Authors’ instructions along with LaTeX and Word macro files are available as well on the web at Springer.


XCBR has been a workshop of ICCBR since 2018, receiving multiple submissions (6-8 papers approx.) from different research groups and having a usual format of half a day. Previous XCBR workshops included an invited talk and oral presentations of accepted papers.

Participants of previous editions will be contacted in order to promote the participation in this fifth edition.


XCBR Challenge

slot 1

11:30 11:45 Opening
11:45 1:00 Contest with iSee team support + Questionnaire completion
1:00 2:00 Lunch
XCBR Workshop

(10-15 minutes per presentation)

2:00 2:05 Welcome
2:05 2:20 • Louenas Bounia, Chafik Anasse and Mathieu Gouliot
Impact of weight functions on preferred abductive explanations for decision trees
2:20 2:35 • Marta Caro-Martínez, Anjana Wijekoon, Belen Diaz-Agudo and Juan A. Recio-Garcia
The Current and Future Role of Visual Question Answering in eXplainable Artificial Intelligence
2:35 2:50 • Betül Bayrak and Kerstin Bach
A Twin XCBR System Using Supportive and Contrastive Explanations
2:50 3:05 • Craig Pirie, Nirmalie Wiratunga, Anjana Wijekoon and Carlos Francisco Moreno-Garcia
Let’s Agree To Disagree: Addressing Explainer Disagreements with Aggregate Attributions and Confidence Metrics
3:05 3:20 • Juan A. Recio-Garcia, Mauricio Gabriel Orozco-Del-Castillo and Jose A. Soladrero
Case-based explanation of classification models for the detection of SQL injection attacks
3:20 3:30 Wrap up
3:30 4:00 Coffee
XCBR Challenge

slot 2

4:00 4:10 Summary of the session
4:10 4:30 Participant presentation in 5-10 mins
4:30 5:00 Award Ceremony
Open discussion 5:00 5:30 QA and Closing + Photos


    • June 2nd     : Paper submission deadline
    • June 16th     : Notification of acceptance
    • June 26th     : Camera-ready submission
    • July 17th 11:00 to 17:30      : Workshop date


This workshop will be held on July, 17th, 2023 as part of the ICCBR 2023 workshop series in Aberdeen, Scotland. This workshop is open to all interested conference participants. The Organizing Committee will select a subset of the submitted papers for oral presentation.


After its successful first edition at XCBR’22 we will organize a contest on explicability using CBR. This challenge will consist on several tasks related to the generation of explanation experiences, evaluation of explanation strategies based on existing explainers in iSee cockpit and new explainers that may be submitted by participants into iSee catalogue, and the application of case-based explanation solutions to machine learning black-boxes. Details on the XCBR challenge’23 are at that page Please check the updated Schedule at the Workshop page


Juan A. Recio García, University Complutense of Madrid, Spain
Belén Díaz Agudo, University Complutense of Madrid, Spain
Chamath Palihawadana, Robert Gordon University, UK

Juan A. Recio García.
C/Prof. José García Santesmases 9, 28040, Madrid, Spain 

XCBR’23 will have the support of the European Project iSee (Intelligent Sharing of Explanation Experiences, participated by several members of ICCBR Program Committee.


Juan A. Recio García, University Complutense of Madrid, Spain
Belén Díaz Agudo, University Complutense of Madrid, Spain
Chamath Palihawadana, Robert Gordon University, UK
Nirmalie Wiratunga, Robert Gordon University, UK
Derek Bridge, University College Cork, Ireland
Rosina Weber, Drexel University, USA
Mark Keane, University College Dublin, Ireland
David Leake, Indiana University, USA
Marta Caro Martinez, University Complutense of Madrid, Spain
Anjana Wijekoon, Robert Gordon University, UK
Kyle Martin, Robert Gordon University, UK
Ikechukwu Nkisi-Orji, Robert Gordon University, UK
Anne Liret, BT France, France
Bruno Freisch, BT France, France