---
_id: '54450'
abstract:
- lang: eng
text: In the last decade, there has been increasing interest in allowing users to
understand how the predictions of machine-learned models come about, thus increasing
transparency and empowering users to understand and potentially contest those
decisions.Dialogue-based approaches, in contrast to traditional one-shot eXplainable
Artificial Intelligence (XAI) methods, facilitate interactive, in-depth exploration
through multi-turn dialogues, simulating expert conversations. This paper reviews
the current state of dialogue-based XAI, presenting a systematic review of 1,339
publications, narrowed down to 14 based on inclusion criteria. We explore theoretical
foundations of the systems, propose key dimensions along which different solutions
to dialogue-based XAI differ, and identify key use cases, target audiences, system
components, and the types of supported queries and responses. Furthermore, we
investigate the current paradigms by which systems are evaluated and highlight
their key limitations. Key findings include identifying the main use cases, objectives,
and audiences targeted by dialogue-based XAI methods, and summarize the main types
of questions and information needs. Beyond discussing avenues for future work,
we present a meta-architecture for these systems from existing literature and
outlined prevalent theoretical frameworks.
article_number: '81'
author:
- first_name: Dimitry
full_name: Mindlin, Dimitry
last_name: Mindlin
- first_name: Fabian
full_name: Beer, Fabian
last_name: Beer
- first_name: Leonie Nora
full_name: Sieger, Leonie Nora
id: '93402'
last_name: Sieger
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Philipp
full_name: Cimiano, Philipp
last_name: Cimiano
- first_name: Elena
full_name: Esposito, Elena
last_name: Esposito
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: 'Mindlin D, Beer F, Sieger LN, et al. Beyond One-Shot Explanations: A Systematic
Literature Review of Dialogue-Based XAI Approaches. Artificial Intelligence
Review. 2025;58(3). doi:10.1007/s10462-024-11007-7'
apa: 'Mindlin, D., Beer, F., Sieger, L. N., Heindorf, S., Cimiano, P., Esposito,
E., & Ngonga Ngomo, A.-C. (2025). Beyond One-Shot Explanations: A Systematic
Literature Review of Dialogue-Based XAI Approaches. Artificial Intelligence
Review, 58(3), Article 81. https://doi.org/10.1007/s10462-024-11007-7'
bibtex: '@article{Mindlin_Beer_Sieger_Heindorf_Cimiano_Esposito_Ngonga Ngomo_2025,
title={Beyond One-Shot Explanations: A Systematic Literature Review of Dialogue-Based
XAI Approaches}, volume={58}, DOI={10.1007/s10462-024-11007-7},
number={381}, journal={Artificial Intelligence Review}, publisher={Springer},
author={Mindlin, Dimitry and Beer, Fabian and Sieger, Leonie Nora and Heindorf,
Stefan and Cimiano, Philipp and Esposito, Elena and Ngonga Ngomo, Axel-Cyrille},
year={2025} }'
chicago: 'Mindlin, Dimitry, Fabian Beer, Leonie Nora Sieger, Stefan Heindorf, Philipp
Cimiano, Elena Esposito, and Axel-Cyrille Ngonga Ngomo. “Beyond One-Shot Explanations:
A Systematic Literature Review of Dialogue-Based XAI Approaches.” Artificial
Intelligence Review 58, no. 3 (2025). https://doi.org/10.1007/s10462-024-11007-7.'
ieee: 'D. Mindlin et al., “Beyond One-Shot Explanations: A Systematic Literature
Review of Dialogue-Based XAI Approaches,” Artificial Intelligence Review,
vol. 58, no. 3, Art. no. 81, 2025, doi: 10.1007/s10462-024-11007-7.'
mla: 'Mindlin, Dimitry, et al. “Beyond One-Shot Explanations: A Systematic Literature
Review of Dialogue-Based XAI Approaches.” Artificial Intelligence Review,
vol. 58, no. 3, 81, Springer, 2025, doi:10.1007/s10462-024-11007-7.'
short: D. Mindlin, F. Beer, L.N. Sieger, S. Heindorf, P. Cimiano, E. Esposito, A.-C.
Ngonga Ngomo, Artificial Intelligence Review 58 (2025).
date_created: 2024-05-26T18:55:58Z
date_updated: 2025-01-24T20:09:20Z
department:
- _id: '760'
- _id: '574'
doi: 10.1007/s10462-024-11007-7
intvolume: ' 58'
issue: '3'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://link.springer.com/article/10.1007/s10462-024-11007-7
oa: '1'
publication: Artificial Intelligence Review
publication_status: published
publisher: Springer
status: public
title: 'Beyond One-Shot Explanations: A Systematic Literature Review of Dialogue-Based
XAI Approaches'
type: journal_article
user_id: '11871'
volume: 58
year: '2025'
...
---
_id: '37937'
abstract:
- lang: eng
text: "Knowledge bases are widely used for information management on the web,\r\nenabling
high-impact applications such as web search, question answering, and\r\nnatural
language processing. They also serve as the backbone for automatic\r\ndecision
systems, e.g. for medical diagnostics and credit scoring. As\r\nstakeholders affected
by these decisions would like to understand their\r\nsituation and verify fair
decisions, a number of explanation approaches have\r\nbeen proposed using concepts
in description logics. However, the learned\r\nconcepts can become long and difficult
to fathom for non-experts, even when\r\nverbalized. Moreover, long concepts do
not immediately provide a clear path of\r\naction to change one's situation. Counterfactuals
answering the question \"How\r\nmust feature values be changed to obtain a different
classification?\" have been\r\nproposed as short, human-friendly explanations
for tabular data. In this paper,\r\nwe transfer the notion of counterfactuals
to description logics and propose the\r\nfirst algorithm for generating counterfactual
explanations in the description\r\nlogic $\\mathcal{ELH}$. Counterfactual candidates
are generated from concepts\r\nand the candidates with fewest feature changes
are selected as counterfactuals.\r\nIn case of multiple counterfactuals, we rank
them according to the likeliness\r\nof their feature combinations. For evaluation,
we conduct a user survey to\r\ninvestigate which of the generated counterfactual
candidates are preferred for\r\nexplanation by participants. In a second study,
we explore possible use cases\r\nfor counterfactual explanations."
author:
- first_name: Leonie Nora
full_name: Sieger, Leonie Nora
id: '93402'
last_name: Sieger
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Lukas
full_name: Blübaum, Lukas
last_name: Blübaum
- first_name: Axel-Cyrille
full_name: Ngonga Ngomo, Axel-Cyrille
id: '65716'
last_name: Ngonga Ngomo
citation:
ama: Sieger LN, Heindorf S, Blübaum L, Ngonga Ngomo A-C. Explaining ELH Concept
Descriptions through Counterfactual Reasoning. arXiv:230105109. Published
online 2023.
apa: Sieger, L. N., Heindorf, S., Blübaum, L., & Ngonga Ngomo, A.-C. (2023).
Explaining ELH Concept Descriptions through Counterfactual Reasoning. In arXiv:2301.05109.
bibtex: '@article{Sieger_Heindorf_Blübaum_Ngonga Ngomo_2023, title={Explaining ELH
Concept Descriptions through Counterfactual Reasoning}, journal={arXiv:2301.05109},
author={Sieger, Leonie Nora and Heindorf, Stefan and Blübaum, Lukas and Ngonga
Ngomo, Axel-Cyrille}, year={2023} }'
chicago: Sieger, Leonie Nora, Stefan Heindorf, Lukas Blübaum, and Axel-Cyrille Ngonga
Ngomo. “Explaining ELH Concept Descriptions through Counterfactual Reasoning.”
ArXiv:2301.05109, 2023.
ieee: L. N. Sieger, S. Heindorf, L. Blübaum, and A.-C. Ngonga Ngomo, “Explaining
ELH Concept Descriptions through Counterfactual Reasoning,” arXiv:2301.05109.
2023.
mla: Sieger, Leonie Nora, et al. “Explaining ELH Concept Descriptions through Counterfactual
Reasoning.” ArXiv:2301.05109, 2023.
short: L.N. Sieger, S. Heindorf, L. Blübaum, A.-C. Ngonga Ngomo, ArXiv:2301.05109
(2023).
date_created: 2023-01-22T19:36:01Z
date_updated: 2024-05-26T19:03:44Z
department:
- _id: '574'
- _id: '760'
external_id:
arxiv:
- '2301.05109'
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://arxiv.org/pdf/2301.05109.pdf
oa: '1'
publication: arXiv:2301.05109
status: public
title: Explaining ELH Concept Descriptions through Counterfactual Reasoning
type: preprint
user_id: '11871'
year: '2023'
...
---
_id: '34674'
abstract:
- lang: eng
text: 'Smart home systems contain plenty of features that enhance wellbeing in everyday
life through artificial intelligence (AI). However, many users feel insecure because
they do not understand the AI’s functionality and do not feel they are in control
of it. Combining technical, psychological and philosophical views on AI, we rethink
smart homes as interactive systems where users can partake in an intelligent agent’s
learning. Parallel to the goals of explainable AI (XAI), we explored the possibility
of user involvement in supervised learning of the smart home to have a first approach
to improve acceptance, support subjective understanding and increase perceived
control. In this work, we conducted two studies: In an online pre-study, we asked
participants about their attitude towards teaching AI via a questionnaire. In
the main study, we performed a Wizard of Oz laboratory experiment with human participants,
where participants spent time in a prototypical smart home and taught activity
recognition to the intelligent agent through supervised learning based on the
user’s behaviour. We found that involvement in the AI’s learning phase enhanced
the users’ feeling of control, perceived understanding and perceived usefulness
of AI in general. The participants reported positive attitudes towards training
a smart home AI and found the process understandable and controllable. We suggest
that involving the user in the learning phase could lead to better personalisation
and increased understanding and control by users of intelligent agents for smart
home automation.'
alternative_title:
- Increasing Perceived Control and Understanding
author:
- first_name: Leonie Nora
full_name: Sieger, Leonie Nora
id: '93402'
last_name: Sieger
- first_name: Julia
full_name: Hermann, Julia
last_name: Hermann
- first_name: Astrid
full_name: Schomäcker, Astrid
last_name: Schomäcker
- first_name: Stefan
full_name: Heindorf, Stefan
id: '11871'
last_name: Heindorf
orcid: 0000-0002-4525-6865
- first_name: Christian
full_name: Meske, Christian
last_name: Meske
- first_name: Celine-Chiara
full_name: Hey, Celine-Chiara
last_name: Hey
- first_name: Ayşegül
full_name: Doğangün, Ayşegül
last_name: Doğangün
citation:
ama: 'Sieger LN, Hermann J, Schomäcker A, et al. User Involvement in Training Smart
Home Agents. In: International Conference on Human-Agent Interaction. ACM;
2022. doi:10.1145/3527188.3561914'
apa: 'Sieger, L. N., Hermann, J., Schomäcker, A., Heindorf, S., Meske, C., Hey,
C.-C., & Doğangün, A. (2022). User Involvement in Training Smart Home Agents.
International Conference on Human-Agent Interaction. HAI ’22: International
Conference on Human-Agent Interaction, Christchurch, New Zealand. https://doi.org/10.1145/3527188.3561914'
bibtex: '@inproceedings{Sieger_Hermann_Schomäcker_Heindorf_Meske_Hey_Doğangün_2022,
title={User Involvement in Training Smart Home Agents}, DOI={10.1145/3527188.3561914},
booktitle={International Conference on Human-Agent Interaction}, publisher={ACM},
author={Sieger, Leonie Nora and Hermann, Julia and Schomäcker, Astrid and Heindorf,
Stefan and Meske, Christian and Hey, Celine-Chiara and Doğangün, Ayşegül}, year={2022}
}'
chicago: Sieger, Leonie Nora, Julia Hermann, Astrid Schomäcker, Stefan Heindorf,
Christian Meske, Celine-Chiara Hey, and Ayşegül Doğangün. “User Involvement in
Training Smart Home Agents.” In International Conference on Human-Agent Interaction.
ACM, 2022. https://doi.org/10.1145/3527188.3561914.
ieee: 'L. N. Sieger et al., “User Involvement in Training Smart Home Agents,”
presented at the HAI ’22: International Conference on Human-Agent Interaction,
Christchurch, New Zealand, 2022, doi: 10.1145/3527188.3561914.'
mla: Sieger, Leonie Nora, et al. “User Involvement in Training Smart Home Agents.”
International Conference on Human-Agent Interaction, ACM, 2022, doi:10.1145/3527188.3561914.
short: 'L.N. Sieger, J. Hermann, A. Schomäcker, S. Heindorf, C. Meske, C.-C. Hey,
A. Doğangün, in: International Conference on Human-Agent Interaction, ACM, 2022.'
conference:
end_date: 2022-12-08
location: Christchurch, New Zealand
name: 'HAI ''22: International Conference on Human-Agent Interaction'
start_date: 2022-12-05
date_created: 2022-12-21T09:48:43Z
date_updated: 2024-05-30T18:04:45Z
ddc:
- '000'
department:
- _id: '574'
- _id: '760'
doi: 10.1145/3527188.3561914
file:
- access_level: closed
content_type: application/pdf
creator: heindorf
date_created: 2024-05-30T18:04:31Z
date_updated: 2024-05-30T18:04:31Z
file_id: '54524'
file_name: User_Involvement_in_Training_Smart_Home_Agents_public.pdf
file_size: 1151728
relation: main_file
success: 1
file_date_updated: 2024-05-30T18:04:31Z
has_accepted_license: '1'
keyword:
- human-agent interaction
- smart homes
- supervised learning
- participation
language:
- iso: eng
main_file_link:
- open_access: '1'
url: https://papers.dice-research.org/2022/HAI_SmartHome/User_Involvement_in_Training_Smart_Home_Agents_public.pdf
oa: '1'
project:
- _id: '121'
grant_number: '438445824'
name: 'TRR 318 - B1: TRR 318 - Subproject B1'
publication: International Conference on Human-Agent Interaction
publication_status: published
publisher: ACM
quality_controlled: '1'
status: public
title: User Involvement in Training Smart Home Agents
type: conference
user_id: '11871'
year: '2022'
...