Accountability of AI Under the Law: The Role of Explanation

By Finale Doshi-Velez, Mason Kortz, Ryan Budish, Christopher T. Bavitz, Samuel J. Gershman, David O'Brien, Stuart Schieber, James Waldo, David Weinberger, Adrian Weller and 1 more. 2017

497 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Health Informatics, Natural Language Processing

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 Health Informatics

In Natural Language Processing

Citations in the corpus

SELFEXPLAIN: A Self-Explaining Architecture for Neural Text Classifiers (2021, background): “Explanations are notoriously difficult to evaluate quantitatively (Doshi-Velez et al., 2017).”
Analysis Methods in Neural Language Processing: A Survey (2018, background): “With the increasing public demand for explaining algorithmic choices in machine learning systems (Doshi-Velez and Kim, 2017; Doshi-Velez et al., 2017), there is pressing need for progress in this direction.”
Sanity Checks for Saliency Maps (2018, background): “As machine learning grows in complexity and impact, much hope rests on explanation methods as tools to elucidate important aspects of learned models [1, 2].”
Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges (2018, methodology): “This information is then used to assess the appropriateness of the outcome in relation to the concerns and values of users (Doran et al., 2017; Wachter et al., 2017; Doshi-Velez et al., 2017; Weller, 2017).”
Local Explanation Methods for Deep Neural Networks Lack Sensitivity to Parameter Values (2018, background): “1 INTRODUCTION Understanding how a trained model derives its output, as well as the factors responsible, is a central challenge in machine learning (Vellido et al., 2012; Doshi-Velez et al., 2017).”
Explaining Explanations in AI (2018, background): “Explanations can be necessary to comply with relevant legislation (Doshi-Velez et al., 2017), verify and improve the functionality of a system (i.e. as a type of ‘debugging’; (Kulesza et al., 2015)) and help developers and humans working with a system learn from it (Samek et al., 2017), and enhance…”
Efficient Search for Diverse Coherent Explanations (2019, background): “Others have called for the use of counterfactuals in explaining machine learning (Doshi-Velez et al., 2017).”
Interpretable Machine Learning in Healthcare (2018, background): “To this end, researchers have tried to elucidate the numerous notions and deﬁnitions of interpretability [17],[8].”
TIP: Typifying the Interpretability of Procedures (2017, background): “One is providing understandable explanations of its action/prediction on specific cases -“Why did the model act this way on this sample?” These explanations are local to a specific decision on a sample and constitute model explanability [15, 44].”
Towards Explainable Artificial Intelligence (2019, background): “But also anti-discrimination and fairness aspects have been widely discussed in the context of AI [28,19].”
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems (2018, background): “…is the occasional case of using the terms Transparent System and Explainable System interchangeably in HCI research [56], while others clarify that explainability is not equivalent to transparency because it does not require knowing the flow of the bits in the AI decision-making process [49].”
The importance of interpretability and visualization in machine learning for applications in medicine and health care (2019, background): “The issue of AI legal accountability has recently been broached by Doshi-Velez et al. [16].”
Explanations in Autonomous Driving: A Survey (2021, background): “[33] conceptualise accountability as the ability to determine whether the decision of a system was made in compliance with procedural and substantive standards, and importantly, to hold one responsible when there is a failure to meet the standards.”
Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunities (2021, background): “Therefore, costs associated with algorithmic explanations should be incurred when the benefits of the explanations outweigh the costs [83].”
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (2019, background): “But also anti-discrimination and fairness aspects have been widely discussed in the context of AI [19,28].”
The fallacy of inscrutability (2018, background): “Such criticisms arise in the context of technical descriptions of complex computer systems or machine learning algorithms [4,5], as part of social critiques of computer systems [3], and in legal scholarship which”