---
_id: '65061'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>\r\n                    One
    of the purposes for which XAI is often brought into play is to enable a user to
    act responsibly. However, responsibility is a complex normative and social phenomenon
    that we unfold in this chapter. We consider that the classical concepts of agency
    and responsibility do not fully capture what is needed for meaningful collaboration
    between human users and XAI. Advocating the perspective of sXAI, we argue that
    the growing adaptivity of AI systems will result in sXAI being considered as partners.
    Both partners adopt particular (dialogical) roles within a collaborative process
    and take responsibility for them. We expect that these roles lead to reactive
    attitudes toward the sXAI on the side of the human partners that make these roles
    relational. They resemble those reactive attitudes that we hold toward other human
    agents. For agents to exercise their responsibility, they need to possess agential
    capacities to fulfill their role with respect to the structure of a social interaction.
    Hence, sXAI can be expected to act responsibly. But because of XAI’s limited normative
    capacities, it might rather act as a marginal agent. We refer to marginal agents
    and show they can be scaffolded with regard to their agential capacities and their
    knowledge about the structure of a social interaction. The structure links the
    actions of the partners to each other in terms of a set of stimuli and responses
    to it in pursuit of a particular goal. Hence, it is important to differentiate
    between the different goals that a structure can impose for exercising responsibility.
    Therefore, we follow (Responsibility from the margins. Oxford University Press;
    2015.\r\n                    <jats:ext-link xmlns:xlink=\"http://www.w3.org/1999/xlink\"
    xlink:href=\"https://doi.org/10.1093/acprof:oso/9780198715672.24001.0001\" ext-link-type=\"uri\">https://doi.org/10.1093/acprof:oso/9780198715672.24001.0001</jats:ext-link>\r\n
    \                   ) and offer three structures that can help to organize responsibility
    for\r\n                    <jats:italic>decisions made</jats:italic>\r\n                    with
    the assistance of AI systems. These structures are attributability, answerability,
    and accountability. Our insights will inform the development and design process
    of XAI to meet the guiding principles of responsible research and innovation as
    well as trustworthy AI.\r\n                  </jats:p>"
author:
- first_name: Katharina J.
  full_name: Rohlfing, Katharina J.
  id: '50352'
  last_name: Rohlfing
  orcid: 0000-0002-5676-8233
- first_name: Suzana
  full_name: Alpsancar, Suzana
  id: '93637'
  last_name: Alpsancar
- first_name: Carsten
  full_name: Schulte, Carsten
  id: '60311'
  last_name: Schulte
citation:
  ama: 'Rohlfing KJ, Alpsancar S, Schulte C. Responsibilities in sXAI. In: <i>Social
    Explainable AI</i>. Springer Nature Singapore; 2026:157-177. doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_9">10.1007/978-981-96-5290-7_9</a>'
  apa: Rohlfing, K. J., Alpsancar, S., &#38; Schulte, C. (2026). Responsibilities
    in sXAI. In <i>Social Explainable AI</i> (pp. 157–177). Springer Nature Singapore.
    <a href="https://doi.org/10.1007/978-981-96-5290-7_9">https://doi.org/10.1007/978-981-96-5290-7_9</a>
  bibtex: '@inbook{Rohlfing_Alpsancar_Schulte_2026, place={Singapore}, title={Responsibilities
    in sXAI}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_9">10.1007/978-981-96-5290-7_9</a>},
    booktitle={Social Explainable AI}, publisher={Springer Nature Singapore}, author={Rohlfing,
    Katharina J. and Alpsancar, Suzana and Schulte, Carsten}, year={2026}, pages={157–177}
    }'
  chicago: 'Rohlfing, Katharina J., Suzana Alpsancar, and Carsten Schulte. “Responsibilities
    in SXAI.” In <i>Social Explainable AI</i>, 157–77. Singapore: Springer Nature
    Singapore, 2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_9">https://doi.org/10.1007/978-981-96-5290-7_9</a>.'
  ieee: 'K. J. Rohlfing, S. Alpsancar, and C. Schulte, “Responsibilities in sXAI,”
    in <i>Social Explainable AI</i>, Singapore: Springer Nature Singapore, 2026, pp.
    157–177.'
  mla: Rohlfing, Katharina J., et al. “Responsibilities in SXAI.” <i>Social Explainable
    AI</i>, Springer Nature Singapore, 2026, pp. 157–77, doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_9">10.1007/978-981-96-5290-7_9</a>.
  short: 'K.J. Rohlfing, S. Alpsancar, C. Schulte, in: Social Explainable AI, Springer
    Nature Singapore, Singapore, 2026, pp. 157–177.'
date_created: 2026-03-19T10:59:18Z
date_updated: 2026-03-19T11:53:01Z
department:
- _id: '26'
- _id: '756'
doi: 10.1007/978-981-96-5290-7_9
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://doi.org/10.1007/978-981-96-5290-7_9
oa: '1'
page: 157-177
place: Singapore
project:
- _id: '109'
  name: 'TRR 318: Erklärbarkeit konstruieren'
- _id: '370'
  name: 'TRR 318; TP B06: Ethik und Normativität der erklärbaren KI'
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: Responsibilities in sXAI
type: book_chapter
user_id: '93637'
year: '2026'
...
---
_id: '65063'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>\r\n                    This
    chapter critically examines how social explainable AI (sXAI) can better support
    AI practitioners in ensuring fairness in AI-based decision-making. We argue for
    a fundamental shift: Fairness should be understood not as a technical property
    or an information problem, but as a matter of vulnerability—focusing on the real-world
    impacts of AI on individuals and groups, especially those most at risk. Hereby,
    we call for a shift in perspective: from fair AI to\r\n                    <jats:italic>tasking
    AI fairly</jats:italic>\r\n                    . To motivate our vulnerability
    approach, we review the “Dutch welfare fraud scandal” (system risk indication—SyRI)
    and current challenges in the field of fair AI/machine learning (ML). Vulnerability
    of a person or members of a definable group of persons is a complex relational
    notion, and not a technical property of a technical system. Accordingly, we suggest
    several nontechnical strategies that hold the promise to compensate for the insufficiency
    of purely technical approaches to fairness and other ethical issues in the practical
    use of AI-based systems. To discuss how sXAI, due to its interactive and adaptive
    social character, might better fulfill this role than current XAI techniques,
    we provide a toy scenario for how sXAI might support the virtuous AI practitioner
    in an ethical inquiry. Finally, we also address challenges and limits of our approach.\r\n
    \                 </jats:p>"
author:
- first_name: Suzana
  full_name: Alpsancar, Suzana
  id: '93637'
  last_name: Alpsancar
- first_name: Eugenia
  full_name: Stamboliev, Eugenia
  last_name: Stamboliev
citation:
  ama: 'Alpsancar S, Stamboliev E. Tasking AI Fairly. How to Empower AI Practitioners
    With sXAI? In: <i>Social Explainable AI</i>. Springer Nature Singapore; 2026:557-581.
    doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_29">10.1007/978-981-96-5290-7_29</a>'
  apa: Alpsancar, S., &#38; Stamboliev, E. (2026). Tasking AI Fairly. How to Empower
    AI Practitioners With sXAI? In <i>Social Explainable AI</i> (pp. 557–581). Springer
    Nature Singapore. <a href="https://doi.org/10.1007/978-981-96-5290-7_29">https://doi.org/10.1007/978-981-96-5290-7_29</a>
  bibtex: '@inbook{Alpsancar_Stamboliev_2026, place={Singapore}, title={Tasking AI
    Fairly. How to Empower AI Practitioners With sXAI?}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_29">10.1007/978-981-96-5290-7_29</a>},
    booktitle={Social Explainable AI}, publisher={Springer Nature Singapore}, author={Alpsancar,
    Suzana and Stamboliev, Eugenia}, year={2026}, pages={557–581} }'
  chicago: 'Alpsancar, Suzana, and Eugenia Stamboliev. “Tasking AI Fairly. How to
    Empower AI Practitioners With SXAI?” In <i>Social Explainable AI</i>, 557–81.
    Singapore: Springer Nature Singapore, 2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_29">https://doi.org/10.1007/978-981-96-5290-7_29</a>.'
  ieee: 'S. Alpsancar and E. Stamboliev, “Tasking AI Fairly. How to Empower AI Practitioners
    With sXAI?,” in <i>Social Explainable AI</i>, Singapore: Springer Nature Singapore,
    2026, pp. 557–581.'
  mla: Alpsancar, Suzana, and Eugenia Stamboliev. “Tasking AI Fairly. How to Empower
    AI Practitioners With SXAI?” <i>Social Explainable AI</i>, Springer Nature Singapore,
    2026, pp. 557–81, doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_29">10.1007/978-981-96-5290-7_29</a>.
  short: 'S. Alpsancar, E. Stamboliev, in: Social Explainable AI, Springer Nature
    Singapore, Singapore, 2026, pp. 557–581.'
date_created: 2026-03-19T11:03:30Z
date_updated: 2026-03-19T11:53:42Z
department:
- _id: '26'
- _id: '756'
doi: 10.1007/978-981-96-5290-7_29
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://doi.org/10.1007/978-981-96-5290-7_29
oa: '1'
page: 557-581
place: Singapore
project:
- _id: '370'
  name: 'TRR 318; TP B06: Ethik und Normativität der erklärbaren KI'
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: Tasking AI Fairly. How to Empower AI Practitioners With sXAI?
type: book_chapter
user_id: '93637'
year: '2026'
...
---
_id: '65064'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>XAI can minimize
    the risks of being manipulated and deceived by AI but in turn entails other specific
    risks. This also applies to sXAI, and the specifically social character of sXAI
    harbors particular risks that designers and developers should be aware of. In
    this chapter, we shall discuss the potential opportunities and risks of sXAI.
    We see a particularly positive potential in the social character of sXAI, which
    lies in the fact that skillful users, including those with “healthy distrust,”
    can use the adaptivity of sXAI to produce an explanation that is actually relevant
    and adequate for them. However, this requires a high level of skills on the part
    of the user and is thus in contrast to the general promise of efficiency in the
    use of AI. A potential risk of XAI is that it can be (even more) persuasive, as
    the interactive involvement and the anthropomorphism strengthen a trustworthy
    appearance/performance (independent of the adequacy of the sXAI performance).</jats:p>"
author:
- first_name: Suzana
  full_name: Alpsancar, Suzana
  id: '93637'
  last_name: Alpsancar
- first_name: Michael
  full_name: Klenk, Michael
  last_name: Klenk
citation:
  ama: 'Alpsancar S, Klenk M. The Risk of Manipulation and Deception in sXAI. In:
    <i>Social Explainable AI</i>. Springer Nature Singapore; 2026:583-616. doi:<a
    href="https://doi.org/10.1007/978-981-96-5290-7_30">10.1007/978-981-96-5290-7_30</a>'
  apa: Alpsancar, S., &#38; Klenk, M. (2026). The Risk of Manipulation and Deception
    in sXAI. In <i>Social Explainable AI</i> (pp. 583–616). Springer Nature Singapore.
    <a href="https://doi.org/10.1007/978-981-96-5290-7_30">https://doi.org/10.1007/978-981-96-5290-7_30</a>
  bibtex: '@inbook{Alpsancar_Klenk_2026, place={Singapore}, title={The Risk of Manipulation
    and Deception in sXAI}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_30">10.1007/978-981-96-5290-7_30</a>},
    booktitle={Social Explainable AI}, publisher={Springer Nature Singapore}, author={Alpsancar,
    Suzana and Klenk, Michael}, year={2026}, pages={583–616} }'
  chicago: 'Alpsancar, Suzana, and Michael Klenk. “The Risk of Manipulation and Deception
    in SXAI.” In <i>Social Explainable AI</i>, 583–616. Singapore: Springer Nature
    Singapore, 2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_30">https://doi.org/10.1007/978-981-96-5290-7_30</a>.'
  ieee: 'S. Alpsancar and M. Klenk, “The Risk of Manipulation and Deception in sXAI,”
    in <i>Social Explainable AI</i>, Singapore: Springer Nature Singapore, 2026, pp.
    583–616.'
  mla: Alpsancar, Suzana, and Michael Klenk. “The Risk of Manipulation and Deception
    in SXAI.” <i>Social Explainable AI</i>, Springer Nature Singapore, 2026, pp. 583–616,
    doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_30">10.1007/978-981-96-5290-7_30</a>.
  short: 'S. Alpsancar, M. Klenk, in: Social Explainable AI, Springer Nature Singapore,
    Singapore, 2026, pp. 583–616.'
date_created: 2026-03-19T11:05:30Z
date_updated: 2026-03-19T11:52:00Z
department:
- _id: '26'
- _id: '756'
doi: 10.1007/978-981-96-5290-7_30
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: ' https://doi.org/10.1007/978-981-96-5290-7_30'
oa: '1'
page: 583-616
place: Singapore
project:
- _id: '109'
  name: 'TRR 318: Erklärbarkeit konstruieren'
- _id: '370'
  name: 'TRR 318; TP B06: Ethik und Normativität der erklärbaren KI'
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: The Risk of Manipulation and Deception in sXAI
type: book_chapter
user_id: '93637'
year: '2026'
...
---
_id: '65065'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>This introduction
    sets the stage for the present book. Whereas research in eXplainable AI (XAI)
    is motivated by societal changes and values, technology development largely ignores
    social aspects. This book aims to address this research gap with a systematic
    and comprehensive social view on explainable AI. Besides introducing many relevant
    concepts, the book offers first access to their possible implementation, thus
    advancing the development of more social XAI. The introduction starts by connecting
    the topic to the general research field of XAI. The second part defines the novel
    approach of social eXplainable AI (sXAI) along the three characteristics of social
    interaction such as patternedness, incrementality, and multimodality. Finally,
    the third part explains the structure followed by each chapter. The book offers
    insights not only for readers who work on technology development but also for
    those working in sociotechnical fields. Addressing an interdisciplinary readership,
    the book is an invitation for more exchange and further development of the sXAI
    field.</jats:p>"
citation:
  ama: Rohlfing KJ, Främling K, Lim B, Alpsancar S, Thommes K, eds. <i>Social Explainable
    AI</i>. Springer Nature Singapore; 2026. doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_1">10.1007/978-981-96-5290-7_1</a>
  apa: Rohlfing, K. J., Främling, K., Lim, B., Alpsancar, S., &#38; Thommes, K. (Eds.).
    (2026). <i>Social Explainable AI</i>. Springer Nature Singapore. <a href="https://doi.org/10.1007/978-981-96-5290-7_1">https://doi.org/10.1007/978-981-96-5290-7_1</a>
  bibtex: '@book{Rohlfing_Främling_Lim_Alpsancar_Thommes_2026, place={Singapore},
    title={Social Explainable AI}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_1">10.1007/978-981-96-5290-7_1</a>},
    publisher={Springer Nature Singapore}, year={2026} }'
  chicago: 'Rohlfing, Katharina J., Kary Främling, Brian Lim, Suzana Alpsancar, and
    Kirsten Thommes, eds. <i>Social Explainable AI</i>. Singapore: Springer Nature
    Singapore, 2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_1">https://doi.org/10.1007/978-981-96-5290-7_1</a>.'
  ieee: 'K. J. Rohlfing, K. Främling, B. Lim, S. Alpsancar, and K. Thommes, Eds.,
    <i>Social Explainable AI</i>. Singapore: Springer Nature Singapore, 2026.'
  mla: Rohlfing, Katharina J., et al., editors. <i>Social Explainable AI</i>. Springer
    Nature Singapore, 2026, doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_1">10.1007/978-981-96-5290-7_1</a>.
  short: K.J. Rohlfing, K. Främling, B. Lim, S. Alpsancar, K. Thommes, eds., Social
    Explainable AI, Springer Nature Singapore, Singapore, 2026.
date_created: 2026-03-19T11:55:17Z
date_updated: 2026-03-19T11:59:42Z
department:
- _id: '26'
- _id: '756'
doi: 10.1007/978-981-96-5290-7_1
editor:
- first_name: Katharina J.
  full_name: Rohlfing, Katharina J.
  id: '50352'
  last_name: Rohlfing
  orcid: 0000-0002-5676-8233
- first_name: Kary
  full_name: Främling, Kary
  last_name: Främling
- first_name: Brian
  full_name: Lim, Brian
  last_name: Lim
- first_name: Suzana
  full_name: Alpsancar, Suzana
  id: '93637'
  last_name: Alpsancar
- first_name: Kirsten
  full_name: Thommes, Kirsten
  id: '72497'
  last_name: Thommes
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://link.springer.com/book/10.1007/978-981-96-5290-7
oa: '1'
place: Singapore
project:
- _id: '109'
  name: 'TRR 318: Erklärbarkeit konstruieren'
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: Social Explainable AI
type: book_editor
user_id: '93637'
year: '2026'
...
---
_id: '65069'
author:
- first_name: Kary
  full_name: Främling, Kary
  last_name: Främling
- first_name: Rachid
  full_name: Alami, Rachid
  last_name: Alami
- first_name: Joris
  full_name: Hulstijn, Joris
  last_name: Hulstijn
- first_name: Igor
  full_name: Tchappi, Igor
  last_name: Tchappi
- first_name: Angela
  full_name: Grimminger, Angela
  id: '57578'
  last_name: Grimminger
- first_name: Britta
  full_name: Wrede, Britta
  last_name: Wrede
- first_name: Hendrik
  full_name: Buschmeier, Hendrik
  last_name: Buschmeier
- first_name: Sylvain
  full_name: Kubler, Sylvain
  last_name: Kubler
citation:
  ama: 'Främling K, Alami R, Hulstijn J, et al. Scenarios of Social Explainable AI
    in practice. In: Rohlfing KJ, Främling K, Alpsancar S, Thommes K, Lim BY, eds.
    <i>Social Explainable AI</i>. Springer; 2026:19-38. doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_2">10.1007/978-981-96-5290-7_2</a>'
  apa: Främling, K., Alami, R., Hulstijn, J., Tchappi, I., Grimminger, A., Wrede,
    B., Buschmeier, H., &#38; Kubler, S. (2026). Scenarios of Social Explainable AI
    in practice. In K. J. Rohlfing, K. Främling, S. Alpsancar, K. Thommes, &#38; B.
    Y. Lim (Eds.), <i>Social Explainable AI</i> (pp. 19–38). Springer. <a href="https://doi.org/10.1007/978-981-96-5290-7_2">https://doi.org/10.1007/978-981-96-5290-7_2</a>
  bibtex: '@inbook{Främling_Alami_Hulstijn_Tchappi_Grimminger_Wrede_Buschmeier_Kubler_2026,
    title={Scenarios of Social Explainable AI in practice}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_2">10.1007/978-981-96-5290-7_2</a>},
    booktitle={Social Explainable AI}, publisher={Springer}, author={Främling, Kary
    and Alami, Rachid and Hulstijn, Joris and Tchappi, Igor and Grimminger, Angela
    and Wrede, Britta and Buschmeier, Hendrik and Kubler, Sylvain}, editor={Rohlfing,
    Katharina J. and Främling, Kary and Alpsancar, Suzana and Thommes, Kirsten and
    Lim, Brian Y.}, year={2026}, pages={19–38} }'
  chicago: Främling, Kary, Rachid Alami, Joris Hulstijn, Igor Tchappi, Angela Grimminger,
    Britta Wrede, Hendrik Buschmeier, and Sylvain Kubler. “Scenarios of Social Explainable
    AI in Practice.” In <i>Social Explainable AI</i>, edited by Katharina J. Rohlfing,
    Kary Främling, Suzana Alpsancar, Kirsten Thommes, and Brian Y. Lim, 19–38. Springer,
    2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_2">https://doi.org/10.1007/978-981-96-5290-7_2</a>.
  ieee: K. Främling <i>et al.</i>, “Scenarios of Social Explainable AI in practice,”
    in <i>Social Explainable AI</i>, K. J. Rohlfing, K. Främling, S. Alpsancar, K.
    Thommes, and B. Y. Lim, Eds. Springer, 2026, pp. 19–38.
  mla: Främling, Kary, et al. “Scenarios of Social Explainable AI in Practice.” <i>Social
    Explainable AI</i>, edited by Katharina J. Rohlfing et al., Springer, 2026, pp.
    19–38, doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_2">10.1007/978-981-96-5290-7_2</a>.
  short: 'K. Främling, R. Alami, J. Hulstijn, I. Tchappi, A. Grimminger, B. Wrede,
    H. Buschmeier, S. Kubler, in: K.J. Rohlfing, K. Främling, S. Alpsancar, K. Thommes,
    B.Y. Lim (Eds.), Social Explainable AI, Springer, 2026, pp. 19–38.'
date_created: 2026-03-20T09:18:01Z
date_updated: 2026-03-20T09:22:08Z
doi: 10.1007/978-981-96-5290-7_2
editor:
- first_name: Katharina J.
  full_name: Rohlfing, Katharina J.
  last_name: Rohlfing
- first_name: Kary
  full_name: Främling, Kary
  last_name: Främling
- first_name: Suzana
  full_name: Alpsancar, Suzana
  last_name: Alpsancar
- first_name: Kirsten
  full_name: Thommes, Kirsten
  last_name: Thommes
- first_name: Brian Y.
  full_name: Lim, Brian Y.
  last_name: Lim
language:
- iso: eng
main_file_link:
- open_access: '1'
oa: '1'
page: 19-38
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer
quality_controlled: '1'
related_material:
  link:
  - relation: original
    url: https://link.springer.com/chapter/10.1007/978-981-96-5290-7_2
status: public
title: Scenarios of Social Explainable AI in practice
type: book_chapter
user_id: '57578'
year: '2026'
...
---
_id: '65090'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>If XAI are
    to become social XAI, XAI methods must have capabilities enabling them to ‘extract’
    information about the underlying AI model and to generate explanatory content
    based on that information. In a dialog between explainer and explainee, the explanans
    presented in every explanation move have to relate to each other understandably
    and coherently in order to remain trustworthy. This signifies that the generated
    explanantia have to be consistent—independently of what question is answered by
    each explanans, in what modality, in what vocabulary, and at what level of abstraction.
    Moreover, it is advantageous to be able to provide a rich palette of different
    kinds of explanantia in order to be able to have a fluent dialog in which the
    explanantia can be generated and adapted to the context, the explainee, feedback,
    reactions during the interaction with the explainee, and so forth. This chapter
    attempts to identify relevant questions that an explainee might ask during an
    explanatory dialog, and it assesses to what extent different XAI methods are capable
    of addressing these questions in a coherent way. The Contextual Importance and
    Utility (CIU) method is used to illustrate how an XAI method can generate explanantia
    for most of the identified questions. CIU also provides a flexibility in how explanatory
    content is generated that makes it possible to create a meaningful dialog with
    the explainee.</jats:p>"
author:
- first_name: Kary
  full_name: Främling, Kary
  last_name: Främling
- first_name: Kirsten
  full_name: Thommes, Kirsten
  id: '72497'
  last_name: Thommes
- first_name: Britta
  full_name: Wrede, Britta
  last_name: Wrede
citation:
  ama: 'Främling K, Thommes K, Wrede B. Generation of Explanatory Content and Requirements
    for Social XAI. In: <i>Social Explainable AI</i>. Springer Nature Singapore; 2026.
    doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_15">10.1007/978-981-96-5290-7_15</a>'
  apa: Främling, K., Thommes, K., &#38; Wrede, B. (2026). Generation of Explanatory
    Content and Requirements for Social XAI. In <i>Social Explainable AI</i>. Springer
    Nature Singapore. <a href="https://doi.org/10.1007/978-981-96-5290-7_15">https://doi.org/10.1007/978-981-96-5290-7_15</a>
  bibtex: '@inbook{Främling_Thommes_Wrede_2026, place={Singapore}, title={Generation
    of Explanatory Content and Requirements for Social XAI}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_15">10.1007/978-981-96-5290-7_15</a>},
    booktitle={Social Explainable AI}, publisher={Springer Nature Singapore}, author={Främling,
    Kary and Thommes, Kirsten and Wrede, Britta}, year={2026} }'
  chicago: 'Främling, Kary, Kirsten Thommes, and Britta Wrede. “Generation of Explanatory
    Content and Requirements for Social XAI.” In <i>Social Explainable AI</i>. Singapore:
    Springer Nature Singapore, 2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_15">https://doi.org/10.1007/978-981-96-5290-7_15</a>.'
  ieee: 'K. Främling, K. Thommes, and B. Wrede, “Generation of Explanatory Content
    and Requirements for Social XAI,” in <i>Social Explainable AI</i>, Singapore:
    Springer Nature Singapore, 2026.'
  mla: Främling, Kary, et al. “Generation of Explanatory Content and Requirements
    for Social XAI.” <i>Social Explainable AI</i>, Springer Nature Singapore, 2026,
    doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_15">10.1007/978-981-96-5290-7_15</a>.
  short: 'K. Främling, K. Thommes, B. Wrede, in: Social Explainable AI, Springer Nature
    Singapore, Singapore, 2026.'
date_created: 2026-03-23T08:48:38Z
date_updated: 2026-03-23T08:49:08Z
department:
- _id: '178'
- _id: '184'
doi: 10.1007/978-981-96-5290-7_15
language:
- iso: eng
place: Singapore
project:
- _id: '113'
  name: TRR 318 - Subproject A3
- _id: '125'
  name: TRR 318 - Subproject C2
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: Generation of Explanatory Content and Requirements for Social XAI
type: book_chapter
user_id: '72497'
year: '2026'
...
---
_id: '65088'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>Quantitatively
    evaluating the benefits of eXplainable Artificial Intelligence (XAI) and social
    XAI for humans is not a trivial pursuit. Therefore, we categorize the potential
    measures in terms of subjective and objective outcomes and short- and long-term
    outcomes of interactive social XAI. When reviewing the current state of the art,
    we observed some measurement problems in the literature: (a) Researchers do not
    clearly state whether they want to measure the inner state of users, users’ behavioral
    response, or the overall AI-human collaborative performance. (b) Moreover, most
    measures implicitly assume that all humans either do not react or improve in attitudes
    or performance. Psychological reactance (feeling or doing the opposite) is usually
    not captured. (c) Many researchers invent their own scale when measuring psychological
    constructs, thereby jeopardizing the validity of their measures and slowing down
    progress in the field, because general evidence and subsequent learning can be
    achieved only by collecting many compatible pieces of evidence. (d) Most studies
    look into short-term outcomes and neglect that experiences in social interactions
    with XAI may evolve and have long-term outcomes not only for the individual but
    also for groups or society at large.</jats:p>"
author:
- first_name: Kirsten
  full_name: Thommes, Kirsten
  id: '72497'
  last_name: Thommes
citation:
  ama: 'Thommes K. Measuring the Outcome of sXAI. In: <i>Social Explainable AI</i>.
    Springer Nature Singapore; 2026. doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_28">10.1007/978-981-96-5290-7_28</a>'
  apa: Thommes, K. (2026). Measuring the Outcome of sXAI. In <i>Social Explainable
    AI</i>. Springer Nature Singapore. <a href="https://doi.org/10.1007/978-981-96-5290-7_28">https://doi.org/10.1007/978-981-96-5290-7_28</a>
  bibtex: '@inbook{Thommes_2026, place={Singapore}, title={Measuring the Outcome of
    sXAI}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_28">10.1007/978-981-96-5290-7_28</a>},
    booktitle={Social Explainable AI}, publisher={Springer Nature Singapore}, author={Thommes,
    Kirsten}, year={2026} }'
  chicago: 'Thommes, Kirsten. “Measuring the Outcome of SXAI.” In <i>Social Explainable
    AI</i>. Singapore: Springer Nature Singapore, 2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_28">https://doi.org/10.1007/978-981-96-5290-7_28</a>.'
  ieee: 'K. Thommes, “Measuring the Outcome of sXAI,” in <i>Social Explainable AI</i>,
    Singapore: Springer Nature Singapore, 2026.'
  mla: Thommes, Kirsten. “Measuring the Outcome of SXAI.” <i>Social Explainable AI</i>,
    Springer Nature Singapore, 2026, doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_28">10.1007/978-981-96-5290-7_28</a>.
  short: 'K. Thommes, in: Social Explainable AI, Springer Nature Singapore, Singapore,
    2026.'
date_created: 2026-03-23T08:45:05Z
date_updated: 2026-03-23T08:45:33Z
department:
- _id: '178'
- _id: '184'
doi: 10.1007/978-981-96-5290-7_28
language:
- iso: eng
place: Singapore
project:
- _id: '113'
  name: TRR 318 - Subproject A3
- _id: '125'
  name: TRR 318 - Subproject C2
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: Measuring the Outcome of sXAI
type: book_chapter
user_id: '72497'
year: '2026'
...
---
_id: '65086'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>Explainable
    AI (XAI) aims to make the decisions and behavior of an AI understandable to the
    people interacting with it and to those affected by its outcomes. To make XAI
    social, real-world XAI systems need to simulate not only the ways in which human
    explainers behave within explanatory dialogs but also the ways in which such dialogs
    can successfully achieve the intended understanding on the explainee’s side. This,
    in turn, requires an operationalization of the three core aspects of social XAI:
    multimodality, incrementality, and patterns. This chapter lays the ground for
    this goal by defining a basic operational model of social interactions that can
    be refined and extended to account for the specificities of any explanatory real-world
    setting. This serves as a basis for summarizing and discussing existing ideas
    from explainability research and related areas in order to operationalize each
    core aspect. Selected examples and case studies illustrate how to concretely realize
    such an operationalization, thereby serving as a starting point for future research
    on social interaction with XAI.</jats:p>"
author:
- first_name: Henning
  full_name: Wachsmuth, Henning
  last_name: Wachsmuth
- first_name: Kirsten
  full_name: Thommes, Kirsten
  id: '72497'
  last_name: Thommes
- first_name: Milad
  full_name: Alshomary, Milad
  last_name: Alshomary
citation:
  ama: 'Wachsmuth H, Thommes K, Alshomary M. Operationalizing Social Interaction.
    In: <i>Social Explainable AI</i>. Springer Nature Singapore; 2026. doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_27">10.1007/978-981-96-5290-7_27</a>'
  apa: Wachsmuth, H., Thommes, K., &#38; Alshomary, M. (2026). Operationalizing Social
    Interaction. In <i>Social Explainable AI</i>. Springer Nature Singapore. <a href="https://doi.org/10.1007/978-981-96-5290-7_27">https://doi.org/10.1007/978-981-96-5290-7_27</a>
  bibtex: '@inbook{Wachsmuth_Thommes_Alshomary_2026, place={Singapore}, title={Operationalizing
    Social Interaction}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_27">10.1007/978-981-96-5290-7_27</a>},
    booktitle={Social Explainable AI}, publisher={Springer Nature Singapore}, author={Wachsmuth,
    Henning and Thommes, Kirsten and Alshomary, Milad}, year={2026} }'
  chicago: 'Wachsmuth, Henning, Kirsten Thommes, and Milad Alshomary. “Operationalizing
    Social Interaction.” In <i>Social Explainable AI</i>. Singapore: Springer Nature
    Singapore, 2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_27">https://doi.org/10.1007/978-981-96-5290-7_27</a>.'
  ieee: 'H. Wachsmuth, K. Thommes, and M. Alshomary, “Operationalizing Social Interaction,”
    in <i>Social Explainable AI</i>, Singapore: Springer Nature Singapore, 2026.'
  mla: Wachsmuth, Henning, et al. “Operationalizing Social Interaction.” <i>Social
    Explainable AI</i>, Springer Nature Singapore, 2026, doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_27">10.1007/978-981-96-5290-7_27</a>.
  short: 'H. Wachsmuth, K. Thommes, M. Alshomary, in: Social Explainable AI, Springer
    Nature Singapore, Singapore, 2026.'
date_created: 2026-03-23T08:42:37Z
date_updated: 2026-03-23T08:43:25Z
department:
- _id: '178'
- _id: '184'
doi: 10.1007/978-981-96-5290-7_27
language:
- iso: eng
place: Singapore
project:
- _id: '113'
  name: TRR 318 - Subproject A3
- _id: '125'
  name: TRR 318 - Subproject C2
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: Operationalizing Social Interaction
type: book_chapter
user_id: '72497'
year: '2026'
...
---
_id: '65091'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>This chapter
    examines key challenges and potential improvements in the areas of user interaction
    and dynamic explanations. It highlights the need for XAI systems to address context
    factors beyond their predefined scope, it points to the potential need to cocreate
    new concepts that are adapted to particular explainees, and it provides a clear
    overview of the XAI system’s underlying knowledge structure and interaction steps.
    Emphasis is placed on mixed-initiative interaction in which the system can lead
    or respond based on the context and the explainee’s reactions while asserting
    the importance of maintaining coherence across consecutive explanations. These
    advances aim to make XAI systems more flexible, interactive, and user-centric.
    An operationalization section outlines how such social XAI systems could be implemented
    based on the XAI capabilities provided by the Contextual Importance and Utility
    XAI method described in the previous chapter.</jats:p>"
author:
- first_name: Kary
  full_name: Främling, Kary
  last_name: Främling
- first_name: Britta
  full_name: Wrede, Britta
  last_name: Wrede
- first_name: Kirsten
  full_name: Thommes, Kirsten
  id: '72497'
  last_name: Thommes
citation:
  ama: 'Främling K, Wrede B, Thommes K. Exploration of Explaining Content. In: <i>Social
    Explainable AI</i>. Springer Nature Singapore; 2026. doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_16">10.1007/978-981-96-5290-7_16</a>'
  apa: Främling, K., Wrede, B., &#38; Thommes, K. (2026). Exploration of Explaining
    Content. In <i>Social Explainable AI</i>. Springer Nature Singapore. <a href="https://doi.org/10.1007/978-981-96-5290-7_16">https://doi.org/10.1007/978-981-96-5290-7_16</a>
  bibtex: '@inbook{Främling_Wrede_Thommes_2026, place={Singapore}, title={Exploration
    of Explaining Content}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_16">10.1007/978-981-96-5290-7_16</a>},
    booktitle={Social Explainable AI}, publisher={Springer Nature Singapore}, author={Främling,
    Kary and Wrede, Britta and Thommes, Kirsten}, year={2026} }'
  chicago: 'Främling, Kary, Britta Wrede, and Kirsten Thommes. “Exploration of Explaining
    Content.” In <i>Social Explainable AI</i>. Singapore: Springer Nature Singapore,
    2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_16">https://doi.org/10.1007/978-981-96-5290-7_16</a>.'
  ieee: 'K. Främling, B. Wrede, and K. Thommes, “Exploration of Explaining Content,”
    in <i>Social Explainable AI</i>, Singapore: Springer Nature Singapore, 2026.'
  mla: Främling, Kary, et al. “Exploration of Explaining Content.” <i>Social Explainable
    AI</i>, Springer Nature Singapore, 2026, doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_16">10.1007/978-981-96-5290-7_16</a>.
  short: 'K. Främling, B. Wrede, K. Thommes, in: Social Explainable AI, Springer Nature
    Singapore, Singapore, 2026.'
date_created: 2026-03-23T08:52:18Z
date_updated: 2026-03-23T08:52:46Z
department:
- _id: '178'
- _id: '184'
doi: 10.1007/978-981-96-5290-7_16
language:
- iso: eng
place: Singapore
project:
- _id: '113'
  name: TRR 318 - Subproject A3
- _id: '125'
  name: TRR 318 - Subproject C2
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: Exploration of Explaining Content
type: book_chapter
user_id: '72497'
year: '2026'
...
---
_id: '65087'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>Much research
    in XAI focuses on single, one-shot interactions, implicitly assuming that interactions
    have no past, no future, and no surroundings. Although this assumption may be
    necessary for many empirical research settings, it is overly simplifying and unrealistic.
    Whereas empirical research focuses on a world in which no social context exists,
    real applications are embedded in a temporal (past and future) and social context.
    Social science research shows that repeated interactions and secondhand knowledge
    in the social space massively affect human attitudes and behaviors. This chapter
    explains how not only repeated interactions between XAI and humans but also the
    social space and secondhand information may affect social XAI research.</jats:p>"
author:
- first_name: Kirsten
  full_name: Thommes, Kirsten
  id: '72497'
  last_name: Thommes
- first_name: Kary
  full_name: Främling, Kary
  last_name: Främling
- first_name: Britta
  full_name: Wrede, Britta
  last_name: Wrede
- first_name: Sylvain
  full_name: Kubler, Sylvain
  last_name: Kubler
citation:
  ama: 'Thommes K, Främling K, Wrede B, Kubler S. Interaction History in Social XAI.
    In: <i>Social Explainable AI</i>. Springer Nature Singapore; 2026. doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_17">10.1007/978-981-96-5290-7_17</a>'
  apa: Thommes, K., Främling, K., Wrede, B., &#38; Kubler, S. (2026). Interaction
    History in Social XAI. In <i>Social Explainable AI</i>. Springer Nature Singapore.
    <a href="https://doi.org/10.1007/978-981-96-5290-7_17">https://doi.org/10.1007/978-981-96-5290-7_17</a>
  bibtex: '@inbook{Thommes_Främling_Wrede_Kubler_2026, place={Singapore}, title={Interaction
    History in Social XAI}, DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_17">10.1007/978-981-96-5290-7_17</a>},
    booktitle={Social Explainable AI}, publisher={Springer Nature Singapore}, author={Thommes,
    Kirsten and Främling, Kary and Wrede, Britta and Kubler, Sylvain}, year={2026}
    }'
  chicago: 'Thommes, Kirsten, Kary Främling, Britta Wrede, and Sylvain Kubler. “Interaction
    History in Social XAI.” In <i>Social Explainable AI</i>. Singapore: Springer Nature
    Singapore, 2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_17">https://doi.org/10.1007/978-981-96-5290-7_17</a>.'
  ieee: 'K. Thommes, K. Främling, B. Wrede, and S. Kubler, “Interaction History in
    Social XAI,” in <i>Social Explainable AI</i>, Singapore: Springer Nature Singapore,
    2026.'
  mla: Thommes, Kirsten, et al. “Interaction History in Social XAI.” <i>Social Explainable
    AI</i>, Springer Nature Singapore, 2026, doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_17">10.1007/978-981-96-5290-7_17</a>.
  short: 'K. Thommes, K. Främling, B. Wrede, S. Kubler, in: Social Explainable AI,
    Springer Nature Singapore, Singapore, 2026.'
date_created: 2026-03-23T08:43:50Z
date_updated: 2026-03-23T08:44:37Z
department:
- _id: '178'
- _id: '184'
doi: 10.1007/978-981-96-5290-7_17
language:
- iso: eng
place: Singapore
project:
- _id: '125'
  name: TRR 318 - Subproject C2
- _id: '113'
  name: TRR 318 - Subproject A3
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: Interaction History in Social XAI
type: book_chapter
user_id: '72497'
year: '2026'
...
---
_id: '65089'
abstract:
- lang: eng
  text: "<jats:title>Abstract</jats:title>\r\n                  <jats:p>In the past,
    there has been much research aiming to evaluate XAI practices—that is, explanations
    that can add to a user’s understanding of “why” or “why not.” However, because
    there is such a huge amount of diversity in social contexts, optimizing for the
    mean neglects the social dimensions of to whom, what, why, when, and where explanations
    are provided. Nonetheless, these dimensions matter. We give some brief examples
    on the accuracy of the mental model (as an example for who?), on measuring explanation
    practices (as an example of what?), on human motivation (as an example of why?),
    on repeated interactions (as an example of when), and on bystander effects (as
    an example of where?). Importantly, controlling for these factors (or randomizing
    them) is as important as attempting to perform external validations.</jats:p>"
author:
- first_name: Kirsten
  full_name: Thommes, Kirsten
  id: '72497'
  last_name: Thommes
citation:
  ama: 'Thommes K. Evaluation Principles. In: <i>Social Explainable AI</i>. Springer
    Nature Singapore; 2026. doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_26">10.1007/978-981-96-5290-7_26</a>'
  apa: Thommes, K. (2026). Evaluation Principles. In <i>Social Explainable AI</i>.
    Springer Nature Singapore. <a href="https://doi.org/10.1007/978-981-96-5290-7_26">https://doi.org/10.1007/978-981-96-5290-7_26</a>
  bibtex: '@inbook{Thommes_2026, place={Singapore}, title={Evaluation Principles},
    DOI={<a href="https://doi.org/10.1007/978-981-96-5290-7_26">10.1007/978-981-96-5290-7_26</a>},
    booktitle={Social Explainable AI}, publisher={Springer Nature Singapore}, author={Thommes,
    Kirsten}, year={2026} }'
  chicago: 'Thommes, Kirsten. “Evaluation Principles.” In <i>Social Explainable AI</i>.
    Singapore: Springer Nature Singapore, 2026. <a href="https://doi.org/10.1007/978-981-96-5290-7_26">https://doi.org/10.1007/978-981-96-5290-7_26</a>.'
  ieee: 'K. Thommes, “Evaluation Principles,” in <i>Social Explainable AI</i>, Singapore:
    Springer Nature Singapore, 2026.'
  mla: Thommes, Kirsten. “Evaluation Principles.” <i>Social Explainable AI</i>, Springer
    Nature Singapore, 2026, doi:<a href="https://doi.org/10.1007/978-981-96-5290-7_26">10.1007/978-981-96-5290-7_26</a>.
  short: 'K. Thommes, in: Social Explainable AI, Springer Nature Singapore, Singapore,
    2026.'
date_created: 2026-03-23T08:47:10Z
date_updated: 2026-03-23T08:47:38Z
department:
- _id: '178'
- _id: '184'
doi: 10.1007/978-981-96-5290-7_26
language:
- iso: eng
place: Singapore
project:
- _id: '113'
  name: TRR 318 - Subproject A3
- _id: '125'
  name: TRR 318 - Subproject C2
publication: Social Explainable AI
publication_identifier:
  isbn:
  - '9789819652891'
  - '9789819652907'
publication_status: published
publisher: Springer Nature Singapore
status: public
title: Evaluation Principles
type: book_chapter
user_id: '72497'
year: '2026'
...