The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AI

Counterfactual explanations (CEs) have emerged as a viable solution for generating comprehensible explanations in the context of explainable artificial intelligence (XAI). A CE provides actionable information to users on how to achieve the desired outcome from a machine learning (ML) model with mini...

Descripción completa

Detalles Bibliográficos
Autores: Suffian, Muhammad, Kuhl, Ulrike, Bogliolo, Alessandro, Alonso Moral, José María
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universidad de Santiago de Compostela (USC)
Repositorio:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
Idioma:inglés
OAI Identifier:oai:dnet:minerva_____::7695748d2d0775b0f991f96a85d8c6e3
Acceso en línea:https://hdl.handle.net/10347/47344
Access Level:acceso abierto
Palabra clave:Explainable AI
Human-centered explanations
Counterfactual explanations
Human behavioral analytics
User study
id ES_56452d7d4e18c9ab6c4fbcf76504fc3c
oai_identifier_str oai:dnet:minerva_____::7695748d2d0775b0f991f96a85d8c6e3
network_acronym_str ES
network_name_str España
repository_id_str
spelling The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AISuffian, MuhammadKuhl, UlrikeBogliolo, AlessandroAlonso Moral, José MaríaExplainable AIHuman-centered explanationsCounterfactual explanationsHuman behavioral analyticsUser studyCounterfactual explanations (CEs) have emerged as a viable solution for generating comprehensible explanations in the context of explainable artificial intelligence (XAI). A CE provides actionable information to users on how to achieve the desired outcome from a machine learning (ML) model with minimal modifications to the input. XAI is crucial for improving transparency and reliability in AI systems, especially for meeting regulations like the General Data Protection Regulation (GDPR) or the European AI Act. However, the integration of CEs into XAI frameworks and their effectiveness in enhancing user trust and cognitive learning remains uncertain and requires further research. We have developed a user study to face this challenge with two user input-driven counterfactual generation XAI approaches: (i) User Feedback-based Counterfactual Explanation (UFCE) and (ii) Diverse Counterfactual Explanation (DiCE). They are integrated within a game-inspired online platform that enables direct comparisons between them.We compared the task performance, understanding, satisfaction, and trust between control and experimental groups, with a total of 101 participants. After curating the collected data, we had 70 users (24 in the control group) who successfully completed the experiment. Participants in the experimental group received explanations generated by UFCE or DiCE. Findings show that explanations generated by UFCE improve users’ learning experiences, resulting in better task performance, comprehension, satisfaction, and trust. Moreover, participants who interacted with UFCE exhibited significantly higher reliance on suggestions than those who interacted with DiCE, what was supported by statistical validation. These results highlight the significance of human-centered XAI methods and promote meaningful cognitive engagement for users. Furthermore, the game-inspired platform is implemented as open-source to promote Open Science, and it is made publicly available along with data collected in the user study to support further investigations and to ensure reproducibility of reported results.ElsevierUniversidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS)20252025-03-1420252025-03-14journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/10347/47344reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostelainstname:Universidad de Santiago de Compostela (USC)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2021-123152OB-C21 INTELIGENCIA ARTIFICIAL EXPLICABLE PARA EL ENVEJECIMIENTO SALUDABLEopen accesshttp://purl.org/coar/access_right/c_abf2© 2025 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license. Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:dnet:minerva_____::7695748d2d0775b0f991f96a85d8c6e32026-06-15T12:47:27Z
dc.title.none.fl_str_mv The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AI
title The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AI
spellingShingle The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AI
Suffian, Muhammad
Explainable AI
Human-centered explanations
Counterfactual explanations
Human behavioral analytics
User study
title_short The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AI
title_full The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AI
title_fullStr The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AI
title_full_unstemmed The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AI
title_sort The Role of User Feedback in Enhancing Understanding and Trust in Counterfactual Explanations for Explainable AI
dc.creator.none.fl_str_mv Suffian, Muhammad
Kuhl, Ulrike
Bogliolo, Alessandro
Alonso Moral, José María
author Suffian, Muhammad
author_facet Suffian, Muhammad
Kuhl, Ulrike
Bogliolo, Alessandro
Alonso Moral, José María
author_role author
author2 Kuhl, Ulrike
Bogliolo, Alessandro
Alonso Moral, José María
author2_role author
author
author
dc.contributor.none.fl_str_mv Universidade de Santiago de Compostela. Centro de Investigación en Tecnoloxías Intelixentes da USC (CiTIUS)
dc.subject.none.fl_str_mv Explainable AI
Human-centered explanations
Counterfactual explanations
Human behavioral analytics
User study
topic Explainable AI
Human-centered explanations
Counterfactual explanations
Human behavioral analytics
User study
description Counterfactual explanations (CEs) have emerged as a viable solution for generating comprehensible explanations in the context of explainable artificial intelligence (XAI). A CE provides actionable information to users on how to achieve the desired outcome from a machine learning (ML) model with minimal modifications to the input. XAI is crucial for improving transparency and reliability in AI systems, especially for meeting regulations like the General Data Protection Regulation (GDPR) or the European AI Act. However, the integration of CEs into XAI frameworks and their effectiveness in enhancing user trust and cognitive learning remains uncertain and requires further research. We have developed a user study to face this challenge with two user input-driven counterfactual generation XAI approaches: (i) User Feedback-based Counterfactual Explanation (UFCE) and (ii) Diverse Counterfactual Explanation (DiCE). They are integrated within a game-inspired online platform that enables direct comparisons between them.We compared the task performance, understanding, satisfaction, and trust between control and experimental groups, with a total of 101 participants. After curating the collected data, we had 70 users (24 in the control group) who successfully completed the experiment. Participants in the experimental group received explanations generated by UFCE or DiCE. Findings show that explanations generated by UFCE improve users’ learning experiences, resulting in better task performance, comprehension, satisfaction, and trust. Moreover, participants who interacted with UFCE exhibited significantly higher reliance on suggestions than those who interacted with DiCE, what was supported by statistical validation. These results highlight the significance of human-centered XAI methods and promote meaningful cognitive engagement for users. Furthermore, the game-inspired platform is implemented as open-source to promote Open Science, and it is made publicly available along with data collected in the user study to support further investigations and to ensure reproducibility of reported results.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-03-14
2025
2025-03-14
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/10347/47344
url https://hdl.handle.net/10347/47344
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2021-123152OB-C21 INTELIGENCIA ARTIFICIAL EXPLICABLE PARA EL ENVEJECIMIENTO SALUDABLE
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
instname:Universidad de Santiago de Compostela (USC)
instname_str Universidad de Santiago de Compostela (USC)
reponame_str Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
collection Minerva. Repositorio Institucional de la Universidad de Santiago de Compostela
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869408367901933568
score 15,812429

Similares en LA Referencia