XAI—Explainable artificial intelligence

By D. Gunning, M. Stefik, Jaesik Choi, Timothy Miller, Simone Stumpf, Guang-Zhong Yang. 2019

1,734 citations recorded by the source corpus.

Explainability is essential for users to effectively understand, trust, and manage powerful artificial intelligence applications. Explainability is essential for users to effectively understand, trust, and manage powerful artificial intelligence applications.

Subfields: Artificial Intelligence, Information Systems and Management

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems and Management

Citations in the corpus

Taxonomy of Risks posed by Language Models (2022, background): “Moreover, explainability and interpretability research is needed as groundwork to measure LM fairness [24, 66, 129].”
Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, methodology): “Besides explaining to individuals, other roles include leveraging existing knowledge for further knowledge discovery and applications and teaching both agents and humans [28].”
Explainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research (2022, background): “However, there is no 517 accepted system available for determining if an XAI sys- 518 tem is more user-intelligent than another XAI system at this 519 time [77].”
A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME (2023, background): “Accordingly, a new field of research has emerged named eXplainable artificial intelligence (XAI) aiming at demystifying ’black box’ models into a more comprehensible form [5].”
Agentic AI: Autonomous Intelligence for Complex Goals—A Comprehensive Survey (2025, positive): “Explainable AI (XAI) [70], [71] techniques have been proposed to offer a more transparent view of the inner workings of these multi-layered decision-making AI models.”
Applications of artificial intelligence for disaster management (2020, methodology): “To address this issue, there have been research efforts made to improve the interpretability and explainability of AI models, such as explainable artificial intelligence (Arrieta et al. 2020; Gunning et al. 2019).”
Survey of Explainable AI Techniques in Healthcare (2023, background): “It is also important to note that the definition of explainability depends on the prediction task, as mentioned in [9].”
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, neutral): “2019 [59], Lipton 2018 [86], Müller et al.”
Artificial intelligence in histopathology: enhancing cancer research and clinical oncology (2022, background): “This may change with the development of explainable AI (XAI) algorithms that also learn explicit abstractions, rules or even natural language descriptions of their decision making 139 .”
Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions (2023, background): “An underlying assumption is that XAI seeks to achieve these desiderata by improving the mental model that a stakeholder has of an underlying AI-system [6,239,253,254].”
The explanation game: a formal framework for interpretable machine learning (2020, positive): “The call for more explainable algorithms has been especially urgent in areas like clinical medicine (Watson et al. 2019) and military operations (Gunning 2017), where user trust is essential and errors could be catastrophic.”
Using cognitive psychology to understand GPT-3 (2022, background): “With the advent of increasingly capable artificial agents comes the urgency to improve our understanding of how they learn and make decisions (1).”
Understanding generative AI output with embedding models (2025, unknown): “As AI models quickly advance, explainable techniques become invaluable for testing, development, and safety, for example, in biomedical applications ( 23 , 69 ).”