Explanations From Intelligent Systems: Theoretical Foundations and Implications for Practice

By Shirley Gregor, Izak Benbasat. 1999

How researchers see this paper

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

Citations in the corpus

Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “Gregor and Benbasat (1999) reviewed a myriad of empirical studies on explanations in Knowledge Based Systems.”
Explain Yourself: A Natural Language Interface for Scrutable Autonomous Robots (2018, background): “Types of explanations include why to provide a trace or reasoning and why not to elaborate on the system’s control method or strategy [4].”
Explaining Explanations in AI (2018, background): “Gregor and Benbasat (1999) support the importance of abnormality, suggesting that users request explanations when an anomaly or abnormal event is detected.”
Explainable Artificial Intelligence: a Systematic Review (2020, background): “Other scholars instead focused on reviewing methods for knowledge-based approaches such as Expert Systems (ES) [32] and Intelligent Systems [33].”
What Do We Want From Explainable Artificial Intelligence (XAI)? - A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research (2021, background): “At the same time, when novice users want to learn how to use a system, they might want detailed explanatory information whereas when expert users want to use the system for task fulfillment, every unnecessary piece of information could lead to the rejection of the system [36].”
A systematic review and taxonomy of explanations in decision support and recommender systems (2017, background): “A number of explanation taxonomies of different granularity levels has been proposed in the literature in the past (Ye and Johnson 1995; Chandrasekaran et al. 1989; Gregor and Benbasat 1999; Lacave and Díez 2002, 2004; Nakatsu 2006; Papadimitriou et al. 2012; Vig et al. 2009; Blanco et al. 2012; Fri”
Why and why not explanations improve the intelligibility of context-aware intelligent systems (2009, background): “In KBS, several expert systems (e.g., MYCIN [9]) provided reasoning trace explanations to support Why, Why Not and How To questions, but the comparative benefits of these were not compared.”
Social Bias Frames: Reasoning about Social and Power Implications of Language (2019, background): “In addition, detailed explanations are much more informative for people to understand and reason about why a statement is potentially harmful against other people (Gregor and Benbasat, 1999; Ribeiro et al., 2016).”
Algorithmic Accountability and Public Reason (2017, background): “…systems can 9 Although, significant challenges in specifying constraints remain; see e.g. (Bostrom, 2003). provide clear explanations of the reasoning behind their outputs (Wick & Slagle, 1989; Gregor & Benbasat, 1999), models trained by machine learning algorithms may not (Lipton, 2015).”
Evaluating and understanding text-based stock price prediction models (2014, background): “Moreover, prior research has shown that the ability to explain a decision support model is of crucial importance for the acceptance of such models (Gregor & Benbasat, 1999; Kayande, De Bruyn, Lilien, Rangaswamy, & van Bruggen, 2008; Martens & Provost, 2014).”
A comparison of instance-level counterfactual explanation algorithms for behavioral and textual data: SEDC, LIME-C and SHAP-C (2019, background): “The importance of understanding individual classification decisions is well-argued in the literature (Gregor and Benbasat 1999; Freitas 2014; Martens and Provost 2014; Goodman and Flaxman 2016; Doshi-Velez and Kim 2017; Ras et al. 2018; Lipton 2018).”
A Study of Automatic Metrics for the Evaluation of Natural Language Explanations (2021, background): “satisfaction, or acceptance of the explanation and the system (Gregor and Benbasat, 1999).”
Explanation in Case-Based Reasoning–Perspectives and Goals (2005, methodology): “As such, this goal also contains the category of justification explanations from Gregor and Benbasat (1999).”
Explaining Data-Driven Document Classifications (2014, background): “As pointed out by Gregor and Benbasat (1999), a user will want an explanation when she perceives an anomaly.”
Assessing demand for intelligibility in context-aware applications (2009, background): “Gregor and Benbasat’s [16] meta-review investigates explanation types that users of knowledge-based systems (KBS) would like to have.”