Explanation and Justification in Machine Learning : A Survey Or

By Or Biran, Courtenay V. Cotton. 2017

554 citations recorded by the source corpus.

Subfields: Safety, Robustness & Interpretability

How researchers see this paper

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

In Safety, Robustness & Interpretability

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Although some recent surveys [8, 13, 10, 14, 15, 16, 17] summarize the upsurge of activity in XAI across sectors and disciplines, this overview aims to cover the creation of a complete unified framework of categories and concepts that allow for scrutiny and understanding of the field of XAI methods.”
Metrics for Explainable AI: Challenges and Prospects (2018, background): “While explainable AI is only now gaining widespread visibility, [there is a] continuous history of work on explanation and can provide a pool of ideas for researchers currently tackling the task of explanation (Biran and Cotton, 2017, p. 4).”
Learning Optimal Decision Trees with SAT (2018, background): “[Biran and Cotton, 2017] provides a recent account of work on XAI.”
Explanation in Artificial Intelligence: Insights from the Social Sciences (2017, methodology): “A justification explains why a decision is good, but does not necessarily aim to give an explanation of the actual decision-making process [9].”
A comprehensive taxonomy for explainable artificial intelligence: a systematic survey of surveys on methods and concepts (2021, background): “Biran & Cotton 2017 [18] R Local explanations and interpretable models 1”
From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2022, background): “The fact that the explanation should be “easily understood” is also emphasized by others: “systems are interpretable if their operations can be understood by a human” [27] and “an interpretation is the mapping of an abstract concept into a domain that the human can make sense of” [173].”
What Do We Want From Explainable Artificial Intelligence (XAI)? - A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research (2021, background): “Regulators call, for instance, for trustworthy systems [5, 6, 10, 11, 29, 96, 115, 131].”
Doubly Right Object Recognition: A Why Prompt for Visual Rationales (2022, background): “Visual recognition models achieve high performance on the classification tasks, yet they often provide vague and unreliable interpretations and rationales [8].”
Explainable AI under contract and tort law: legal incentives and technical challenges (2020, background): “Different models differ widely in the degree to which the decisive features and weights of the model can be extracted (Burrell 2016).”
Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processing (2021, background): “It 27 complements other explainable AI (XAI) surveys and critical retrospectives that focus on definitions, 28 methods, and/or evaluation [32, 14, 75, 1, 100, 49, 41, 130, 25, 43, 79, 118, 11, 83, 52, 18], but 29 not on datasets.”
Towards Explainable Neural-Symbolic Visual Reasoning (2019, methodology): “Since the definition of interpretability is subject to debate in the scientific community, we will use here the one proposed in Biran and Cotton [2017]:”
Gamut: A Design Probe to Understand How Data Scientists Understand Machine Learning Models (2019, background): “While existing definitions of interpretability center on human understanding, they vary in the aspect of the model to be understood: its internals [20], operations [4], mapping of data [48], or representation [54].”