---
_id: '51368'
abstract:
- lang: eng
text: Dealing with opaque algorithms, the frequent overlap between transparency
and explainability produces seemingly unsolvable dilemmas, as the much-discussed
trade-off between model performance and model transparency. Referring to Niklas
Luhmann's notion of communication, the paper argues that explainability does not
necessarily require transparency and proposes an alternative approach. Explanations
as communicative processes do not imply any disclosure of thoughts or neural processes,
but only reformulations that provide the partners with additional elements and
enable them to understand (from their perspective) what has been done and why.
Recent computational approaches aiming at post-hoc explainability reproduce what
happens in communication, producing explanations of the working of algorithms
that can be different from the processes of the algorithms.
author:
- first_name: 'Elena '
full_name: 'Esposito, Elena '
last_name: Esposito
citation:
ama: Esposito E. Does Explainability Require Transparency? Sociologica. 2023;16(3):17-27.
doi:10.6092/ISSN.1971-8853/15804
apa: Esposito, E. (2023). Does Explainability Require Transparency? Sociologica,
16(3), 17–27. https://doi.org/10.6092/ISSN.1971-8853/15804
bibtex: '@article{Esposito_2023, title={Does Explainability Require Transparency?},
volume={16}, DOI={10.6092/ISSN.1971-8853/15804},
number={3}, journal={Sociologica}, author={Esposito, Elena }, year={2023}, pages={17–27}
}'
chicago: 'Esposito, Elena . “Does Explainability Require Transparency?” Sociologica
16, no. 3 (2023): 17–27. https://doi.org/10.6092/ISSN.1971-8853/15804.'
ieee: 'E. Esposito, “Does Explainability Require Transparency?,” Sociologica,
vol. 16, no. 3, pp. 17–27, 2023, doi: 10.6092/ISSN.1971-8853/15804.'
mla: Esposito, Elena. “Does Explainability Require Transparency?” Sociologica,
vol. 16, no. 3, 2023, pp. 17–27, doi:10.6092/ISSN.1971-8853/15804.
short: E. Esposito, Sociologica 16 (2023) 17–27.
date_created: 2024-02-18T10:16:43Z
date_updated: 2024-02-26T08:46:26Z
department:
- _id: '660'
doi: 10.6092/ISSN.1971-8853/15804
intvolume: ' 16'
issue: '3'
keyword:
- Explainable AI
- Transparency
- Explanation
- Communication
- Sociological systems theory
language:
- iso: eng
page: 17-27
project:
- _id: '121'
grant_number: '438445824'
name: 'TRR 318 - B01: TRR 318 - Ein dialogbasierter Ansatz zur Erklärung von Modellen
des maschinellen Lernens (Teilprojekt B01)'
publication: Sociologica
status: public
title: Does Explainability Require Transparency?
type: journal_article
user_id: '54779'
volume: 16
year: '2023'
...
---
_id: '51369'
abstract:
- lang: eng
text: This short introduction presents the symposium ‘Explaining Machines’. It locates
the debate about Explainable AI in the history of the reflection about AI and
outlines the issues discussed in the contributions.
author:
- first_name: Elena
full_name: Esposito, Elena
last_name: Esposito
citation:
ama: 'Esposito E. Explaining Machines: Social Management of Incomprehensible Algorithms.
Introduction. Sociologica. 2023;16(3):1-4. doi:10.6092/ISSN.1971-8853/16265'
apa: 'Esposito, E. (2023). Explaining Machines: Social Management of Incomprehensible
Algorithms. Introduction. Sociologica, 16(3), 1–4. https://doi.org/10.6092/ISSN.1971-8853/16265'
bibtex: '@article{Esposito_2023, title={Explaining Machines: Social Management of
Incomprehensible Algorithms. Introduction}, volume={16}, DOI={10.6092/ISSN.1971-8853/16265},
number={3}, journal={Sociologica}, author={Esposito, Elena}, year={2023}, pages={1–4}
}'
chicago: 'Esposito, Elena. “Explaining Machines: Social Management of Incomprehensible
Algorithms. Introduction.” Sociologica 16, no. 3 (2023): 1–4. https://doi.org/10.6092/ISSN.1971-8853/16265.'
ieee: 'E. Esposito, “Explaining Machines: Social Management of Incomprehensible
Algorithms. Introduction,” Sociologica, vol. 16, no. 3, pp. 1–4, 2023,
doi: 10.6092/ISSN.1971-8853/16265.'
mla: 'Esposito, Elena. “Explaining Machines: Social Management of Incomprehensible
Algorithms. Introduction.” Sociologica, vol. 16, no. 3, 2023, pp. 1–4,
doi:10.6092/ISSN.1971-8853/16265.'
short: E. Esposito, Sociologica 16 (2023) 1–4.
date_created: 2024-02-18T10:23:23Z
date_updated: 2024-02-26T08:45:56Z
department:
- _id: '660'
doi: 10.6092/ISSN.1971-8853/16265
intvolume: ' 16'
issue: '3'
keyword:
- Explainable AI
- Inexplicability
- Transparency
- Explanation
- Opacity
- Contestability
language:
- iso: eng
page: 1-4
project:
- _id: '121'
grant_number: '438445824'
name: 'TRR 318 - B01: TRR 318 - Ein dialogbasierter Ansatz zur Erklärung von Modellen
des maschinellen Lernens (Teilprojekt B01)'
publication: Sociologica
status: public
title: 'Explaining Machines: Social Management of Incomprehensible Algorithms. Introduction'
type: journal_article
user_id: '54779'
volume: 16
year: '2023'
...
---
_id: '45299'
abstract:
- lang: eng
text: Many applications are driven by Machine Learning (ML) today. While complex
ML models lead to an accurate prediction, their inner decision-making is obfuscated.
However, especially for high-stakes decisions, interpretability and explainability
of the model are necessary. Therefore, we develop a holistic interpretability
and explainability framework (HIEF) to objectively describe and evaluate an intelligent
system’s explainable AI (XAI) capacities. This guides data scientists to create
more transparent models. To evaluate our framework, we analyse 50 real estate
appraisal papers to ensure the robustness of HIEF. Additionally, we identify six
typical types of intelligent systems, so-called archetypes, which range from explanatory
to predictive, and demonstrate how researchers can use the framework to identify
blind-spot topics in their domain. Finally, regarding comprehensiveness, we used
a random sample of six intelligent systems and conducted an applicability check
to provide external validity.
author:
- first_name: Jan-Peter
full_name: Kucklick, Jan-Peter
id: '77066'
last_name: Kucklick
citation:
ama: 'Kucklick J-P. HIEF: a holistic interpretability and explainability framework.
Journal of Decision Systems. Published online 2023:1-41. doi:10.1080/12460125.2023.2207268'
apa: 'Kucklick, J.-P. (2023). HIEF: a holistic interpretability and explainability
framework. Journal of Decision Systems, 1–41. https://doi.org/10.1080/12460125.2023.2207268'
bibtex: '@article{Kucklick_2023, title={HIEF: a holistic interpretability and explainability
framework}, DOI={10.1080/12460125.2023.2207268},
journal={Journal of Decision Systems}, publisher={Taylor & Francis}, author={Kucklick,
Jan-Peter}, year={2023}, pages={1–41} }'
chicago: 'Kucklick, Jan-Peter. “HIEF: A Holistic Interpretability and Explainability
Framework.” Journal of Decision Systems, 2023, 1–41. https://doi.org/10.1080/12460125.2023.2207268.'
ieee: 'J.-P. Kucklick, “HIEF: a holistic interpretability and explainability framework,”
Journal of Decision Systems, pp. 1–41, 2023, doi: 10.1080/12460125.2023.2207268.'
mla: 'Kucklick, Jan-Peter. “HIEF: A Holistic Interpretability and Explainability
Framework.” Journal of Decision Systems, Taylor & Francis, 2023, pp.
1–41, doi:10.1080/12460125.2023.2207268.'
short: J.-P. Kucklick, Journal of Decision Systems (2023) 1–41.
date_created: 2023-05-26T05:04:45Z
date_updated: 2023-05-26T05:08:36Z
department:
- _id: '195'
- _id: '196'
doi: 10.1080/12460125.2023.2207268
keyword:
- Explainable AI (XAI)
- machine learning
- interpretability
- real estate appraisal
- framework
- taxonomy
language:
- iso: eng
main_file_link:
- url: https://www.tandfonline.com/doi/full/10.1080/12460125.2023.2207268
page: 1-41
publication: Journal of Decision Systems
publication_identifier:
issn:
- 1246-0125
- 2116-7052
publication_status: published
publisher: Taylor & Francis
status: public
title: 'HIEF: a holistic interpretability and explainability framework'
type: journal_article
user_id: '77066'
year: '2023'
...
---
_id: '56477'
abstract:
- lang: eng
text: We describe a prototype of a Clinical Decision Support System (CDSS) that
provides (counterfactual) explanations to support accurate medical diagnosis.
The prototype is based on an inherently interpretable Bayesian network (BN). Our
research aims to investigate which explanations are most useful for medical experts
and whether co-constructing explanations can foster trust and acceptance of CDSS.
author:
- first_name: Felix
full_name: Liedeker, Felix
id: '93275'
last_name: Liedeker
- first_name: Philipp
full_name: Cimiano, Philipp
last_name: Cimiano
citation:
ama: 'Liedeker F, Cimiano P. A Prototype of an Interactive Clinical Decision Support
System with Counterfactual Explanations. In: ; 2023.'
apa: Liedeker, F., & Cimiano, P. (2023). A Prototype of an Interactive Clinical
Decision Support System with Counterfactual Explanations. xAI-2023 Late-breaking
Work, Demos and Doctoral Consortium co-located with the 1st World Conference on
eXplainable Artificial Intelligence (xAI-2023), Lissabon.
bibtex: '@inproceedings{Liedeker_Cimiano_2023, title={A Prototype of an Interactive
Clinical Decision Support System with Counterfactual Explanations}, author={Liedeker,
Felix and Cimiano, Philipp}, year={2023} }'
chicago: Liedeker, Felix, and Philipp Cimiano. “A Prototype of an Interactive Clinical
Decision Support System with Counterfactual Explanations,” 2023.
ieee: F. Liedeker and P. Cimiano, “A Prototype of an Interactive Clinical Decision
Support System with Counterfactual Explanations,” presented at the xAI-2023 Late-breaking
Work, Demos and Doctoral Consortium co-located with the 1st World Conference on
eXplainable Artificial Intelligence (xAI-2023), Lissabon, 2023.
mla: Liedeker, Felix, and Philipp Cimiano. A Prototype of an Interactive Clinical
Decision Support System with Counterfactual Explanations. 2023.
short: 'F. Liedeker, P. Cimiano, in: 2023.'
conference:
end_date: 2023-07-28
location: Lissabon
name: xAI-2023 Late-breaking Work, Demos and Doctoral Consortium co-located with
the 1st World Conference on eXplainable Artificial Intelligence (xAI-2023)
start_date: 2023-07-26
date_created: 2024-10-09T14:50:09Z
date_updated: 2024-10-09T15:04:53Z
department:
- _id: '660'
keyword:
- Explainable AI
- Clinical decision support
- Bayesian network
- Counterfactual explanations
language:
- iso: eng
project:
- _id: '128'
name: 'TRR 318 - C5: TRR 318 - Subproject C5'
status: public
title: A Prototype of an Interactive Clinical Decision Support System with Counterfactual
Explanations
type: conference
user_id: '93275'
year: '2023'
...