Defining Explanation in Probabilistic Systems

By Urszula Chajewska, Joseph Y. Halpern. 1997

As probabilistic systems gain popularity and are coming into wider use, the need for a mechanism that explains the system's findings and recommendations becomes more critical. The system will also need a mechanism for ordering competing explanations. We examine two representative approaches to explanation in the literature-- one due to Gardenfors and one due to Pearl--and show that both suffer from significant problems. We propose an approach to defining a notion of "better explanation" that combines some of the features of both together with more recent work by Pearl and others on causality.

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, neutral): “(Chajewska and Halpern, 1997; Chan and Darwiche, 2012; Chang, Gerrish, Wang, Boyd-Graber, and Blei, 2009; Doyle et al., 2003; Druzdzel, 1990, 1996a, 1996b; Druzdzel and Henrion, 1990; Eaves Jr and Shafto, 2016; Fox, Glasspool, Grecu, Modgil, South, and Patkar, 2007; Freuder, Likitvivatanavong, and…”
Minimal Sufficient Explanations for Factored Markov Decision Processes (2009, methodology): “We plan to extend our work to partially observable MDPs.”
Causes and explanations in the structural-model approach: Tractable cases (2002, background): “A critical examin ation of such approaches from the viewpoint of explanations in probabilistic systems is given in [2].”
Causes and explanations: A structural-model approach (2000, methodology): “(A similar point is made in [Chajewska and Halpern 1997].)”
Axiomatizing Causal Reasoning (1998, background): “…role of causal reasoning—in prediction, explanation, and counterfactual reasoning—has been argued eloquently in a number of recent papers and books (Chajewska & Halpern, 1997; Heckerman & Shachter, 1995; Henrion & Druzdzel, 1990; Druzdzel & Simon, 1993; Pearl, 1995; Pearl & Verma, 1991; Spirtes,…”
Explanation and Justification in Machine Learning : A Survey Or (2017, background): “[Chajewska and Halpern, 1997] proposed a formal deﬁnition of explanation in general probabilistic systems, after examining two contemporary ideas and ﬁnding them incomplete.”
Explainable Artificial Intelligence: a Systematic Review (2020, methodology): “The explanandum is something unexpected by the user that creates dissonance with his/her beliefs [58] Correctability The capacity of a method for explainability to allow end-users make technical adjustments to an underlying model [60, 61] Simplification The capacity to reduce the number of variables”
Causes and Explanations: A Structural-Model Approach. Part II: Explanations (2001, background): “(See [Chajewska and Halpern, 1997; Gärdenfors, 1988; Hempel, 1965; Pearl, 1988; Salmon, 1989] and the references therein for an introduction to and discussion of the issues.”