No Cover Image

Conference Paper/Proceeding/Abstract 112 views 9 downloads

Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction

Alan Dix, Tommaso Turchi Orcid Logo, Ben Wilson Orcid Logo, Alessio Malizia Orcid Logo, Anna Monreale Orcid Logo, Matt Roach Orcid Logo

SYNERGY 2025 – Designing and Building Hybrid Human–AI Systems, Volume: 4074

Swansea University Authors: Alan Dix, Ben Wilson Orcid Logo, Matt Roach Orcid Logo

  • Synergy 2025 Coherence.pdf

    PDF | Version of Record

    © 2025 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

    Download (1.47MB)

Check full text

Abstract

Can we create explanations of artificial intelligence and machine learning that have some level of consistency over time as we might expect of a human explanation? This paper explores this issue, and offers several strategies for either maintaining a level of consistency or highlighting when and why...

Full description

Published in: SYNERGY 2025 – Designing and Building Hybrid Human–AI Systems
ISSN: 1613-0073
Published: CEUR-WS.org 2025
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa71398
first_indexed 2026-02-10T13:11:25Z
last_indexed 2026-03-14T05:33:56Z
id cronfa71398
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-03-13T13:34:16.3779060</datestamp><bib-version>v2</bib-version><id>71398</id><entry>2026-02-10</entry><title>Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction</title><swanseaauthors><author><sid>e31e47c578b2a6a39949aa7f149f4cf9</sid><firstname>Alan</firstname><surname>Dix</surname><name>Alan Dix</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>a854728f3952ca0b74a49f9286a9b0e2</sid><ORCID>0009-0004-5663-5854</ORCID><firstname>Ben</firstname><surname>Wilson</surname><name>Ben Wilson</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>9722c301d5bbdc96e967cdc629290fec</sid><ORCID>0000-0002-1486-5537</ORCID><firstname>Matt</firstname><surname>Roach</surname><name>Matt Roach</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-02-10</date><abstract>Can we create explanations of artificial intelligence and machine learning that have some level of consistency over time as we might expect of a human explanation? This paper explores this issue, and offers several strategies for either maintaining a level of consistency or highlighting when and why past explanations might appear inconsistent with current decisions.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>SYNERGY 2025 &#x2013; Designing and Building Hybrid Human&#x2013;AI Systems</journal><volume>4074</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>CEUR-WS.org</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1613-0073</issnElectronic><keywords>human-AI interaction, explainable AI, synergistic human-AI systems, user interface, artificial intelligence, design, adaptive interfaces, user experience</keywords><publishedDay>16</publishedDay><publishedMonth>6</publishedMonth><publishedYear>2025</publishedYear><publishedDate>2025-06-16</publishedDate><doi/><url>https://ceur-ws.org/Vol-4074/</url><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders>Tango Project (EU Grant Agreement no. 101120763 - TANGO)</funders><projectreference/><lastEdited>2026-03-13T13:34:16.3779060</lastEdited><Created>2026-02-10T12:56:53.9026773</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Alan</firstname><surname>Dix</surname><order>1</order></author><author><firstname>Tommaso</firstname><surname>Turchi</surname><orcid>0000-0001-6826-9688</orcid><order>2</order></author><author><firstname>Ben</firstname><surname>Wilson</surname><orcid>0009-0004-5663-5854</orcid><order>3</order></author><author><firstname>Alessio</firstname><surname>Malizia</surname><orcid>0000-0002-2601-7009</orcid><order>4</order></author><author><firstname>Anna</firstname><surname>Monreale</surname><orcid>0000-0001-8541-0284</orcid><order>5</order></author><author><firstname>Matt</firstname><surname>Roach</surname><orcid>0000-0002-1486-5537</orcid><order>6</order></author></authors><documents><document><filename>71398__36218__1ef53d7e0dce4f25841ba519014a458b.pdf</filename><originalFilename>Synergy 2025 Coherence.pdf</originalFilename><uploaded>2026-02-10T13:11:06.0300428</uploaded><type>Output</type><contentLength>1540928</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2025 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/deed.en</licence></document></documents><OutputDurs/></rfc1807>
spelling 2026-03-13T13:34:16.3779060 v2 71398 2026-02-10 Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction e31e47c578b2a6a39949aa7f149f4cf9 Alan Dix Alan Dix true false a854728f3952ca0b74a49f9286a9b0e2 0009-0004-5663-5854 Ben Wilson Ben Wilson true false 9722c301d5bbdc96e967cdc629290fec 0000-0002-1486-5537 Matt Roach Matt Roach true false 2026-02-10 Can we create explanations of artificial intelligence and machine learning that have some level of consistency over time as we might expect of a human explanation? This paper explores this issue, and offers several strategies for either maintaining a level of consistency or highlighting when and why past explanations might appear inconsistent with current decisions. Conference Paper/Proceeding/Abstract SYNERGY 2025 – Designing and Building Hybrid Human–AI Systems 4074 CEUR-WS.org 1613-0073 human-AI interaction, explainable AI, synergistic human-AI systems, user interface, artificial intelligence, design, adaptive interfaces, user experience 16 6 2025 2025-06-16 https://ceur-ws.org/Vol-4074/ COLLEGE NANME COLLEGE CODE Swansea University Not Required Tango Project (EU Grant Agreement no. 101120763 - TANGO) 2026-03-13T13:34:16.3779060 2026-02-10T12:56:53.9026773 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Alan Dix 1 Tommaso Turchi 0000-0001-6826-9688 2 Ben Wilson 0009-0004-5663-5854 3 Alessio Malizia 0000-0002-2601-7009 4 Anna Monreale 0000-0001-8541-0284 5 Matt Roach 0000-0002-1486-5537 6 71398__36218__1ef53d7e0dce4f25841ba519014a458b.pdf Synergy 2025 Coherence.pdf 2026-02-10T13:11:06.0300428 Output 1540928 application/pdf Version of Record true © 2025 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). true eng https://creativecommons.org/licenses/by/4.0/deed.en
title Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction
spellingShingle Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction
Alan Dix
Ben Wilson
Matt Roach
title_short Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction
title_full Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction
title_fullStr Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction
title_full_unstemmed Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction
title_sort Maintaining Coherence in Explainable AI: Strategies for Consistency Across Time and Interaction
author_id_str_mv e31e47c578b2a6a39949aa7f149f4cf9
a854728f3952ca0b74a49f9286a9b0e2
9722c301d5bbdc96e967cdc629290fec
author_id_fullname_str_mv e31e47c578b2a6a39949aa7f149f4cf9_***_Alan Dix
a854728f3952ca0b74a49f9286a9b0e2_***_Ben Wilson
9722c301d5bbdc96e967cdc629290fec_***_Matt Roach
author Alan Dix
Ben Wilson
Matt Roach
author2 Alan Dix
Tommaso Turchi
Ben Wilson
Alessio Malizia
Anna Monreale
Matt Roach
format Conference Paper/Proceeding/Abstract
container_title SYNERGY 2025 – Designing and Building Hybrid Human–AI Systems
container_volume 4074
publishDate 2025
institution Swansea University
issn 1613-0073
publisher CEUR-WS.org
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
url https://ceur-ws.org/Vol-4074/
document_store_str 1
active_str 0
description Can we create explanations of artificial intelligence and machine learning that have some level of consistency over time as we might expect of a human explanation? This paper explores this issue, and offers several strategies for either maintaining a level of consistency or highlighting when and why past explanations might appear inconsistent with current decisions.
published_date 2025-06-16T05:33:59Z
_version_ 1860792105673162752
score 11.100225

Similar Items