Beware of “Explanations” of AI

Abstract Understanding the decisions made and actions taken by increasingly complex AI systems remains a key challenge. This has led to an expanding field of research in explainable artificial intelligence (XAI), highlighting the potential of explanations to enhance trust, support adoption, and meet regulatory standards. However, the question of what constitutes a “good” explanation is dependent on the goals, stakeholders, and context. At a high level, psychological insights such as the concept of mental model alignment can offer guidance, but success in practice is challenging due to social and technical factors. As a result of this ill-defined nature of the problem, explanations can be of poor quality (e.g., unfaithful, irrelevant, or incoherent), potentially leading to substantial risks. Instead of fostering trust and safety, poorly designed explanations can actually cause harm due to wrong decisions, privacy violations, manipulation, and reduced AI adoption. Therefore, we caution stakeholders to beware of explanations of AI: While they can be vital, they are not automatically a remedy for transparency or responsible AI adoption, and their misuse or limitations can exacerbate harm. Attention to these caveats can help guide future research to improve the quality and impact of AI explanations.

Authors

Institutions

Publication Details

Journal
Business & Information Systems Engineering
Published
2026-08-25
DOI
https://doi.org/10.1007/s12599-026-01015-y
Citations
1
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
article
Field-Weighted Citation Impact
6.94

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
article

Beware of “Explanations” of AI

Claudia Perlich, Galit Shmueli, Theodoros Evgeniou, Foster Provost et al.
1 citations
Business & Information Systems Engineering
Explainable Artificial Intelligence (XAI)
6.94
article

Beware of “Explanations” of AI

Claudia Perlich, Galit Shmueli, Theodoros Evgeniou, Foster Provost, Mathias Kraus, Patrick Zschech, Christian Janiesch, Travis Greene, Niklas Kühl, Sofie Goethals, Wouter Verbeke, Stefan Feuerriegel, David Martens, Nadja Klein, Alona Zharova, Kevin Bauer, Sebastian Gabel
article en
1 citations

Abstract

Abstract Understanding the decisions made and actions taken by increasingly complex AI systems remains a key challenge. This has led to an expanding field of research in explainable artificial intelligence (XAI), highlighting the potential of explanations to enhance trust, support adoption, and meet regulatory standards. However, the question of what constitutes a “good” explanation is dependent on the goals, stakeholders, and context. At a high level, psychological insights such as the concept of mental model alignment can offer guidance, but success in practice is challenging due to social and technical factors. As a result of this ill-defined nature of the problem, explanations can be of poor quality (e.g., unfaithful, irrelevant, or incoherent), potentially leading to substantial risks. Instead of fostering trust and safety, poorly designed explanations can actually cause harm due to wrong decisions, privacy violations, manipulation, and reduced AI adoption. Therefore, we caution stakeholders to beware of explanations of AI: While they can be vital, they are not automatically a remedy for transparency or responsible AI adoption, and their misuse or limitations can exacerbate harm. Attention to these caveats can help guide future research to improve the quality and impact of AI explanations.

Business & Information Systems Engineering
INSEAD (FR), Karlsruhe Institute of Technology (DE), Goethe University Frankfurt (DE), University of Antwerp (BE), Copenhagen Business School (DK), TU Dortmund University (DE), National Tsing Hua University (TW), Munich School of Philosophy (DE), Humboldt-Universität zu Berlin (DE), Fraunhofer Institute for Applied Information Technology (DE), University of Bayreuth (DE), New York University (US), University of Regensburg (DE), Technische Universität Dresden (DE), Ludwig-Maximilians-Universität München (DE), Erasmus University Rotterdam (NL), KU Leuven (BE)
Technische Universität Dortmund
Openalex Percentile: Top 7%
Explainable Artificial Intelligence (XAI)
6.94
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.