Eliminating The Impossible, Whatever Remains Must Be True

• URL: http://arxiv.org/abs/2206.09551v1
• Date: Mon, 20 Jun 2022 03:18:14 GMT
• Title: Eliminating The Impossible, Whatever Remains Must Be True
• Authors: Jinqiang Yu, Alexey Ignatiev, Peter J. Stuckey, Nina Narodytska, Joao Marques-Silva
• Abstract summary: We show how one can apply background knowledge to give more succinct "why" formal explanations. We also show how to use existing rule induction techniques to efficiently extract background information from a dataset.
• Score: 46.39428193548396
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rise of AI methods to make predictions and decisions has led to a pressing need for more explainable artificial intelligence (XAI) methods. One common approach for XAI is to produce a post-hoc explanation, explaining why a black box ML model made a certain prediction. Formal approaches to post-hoc explanations provide succinct reasons for why a prediction was made, as well as why not another prediction was made. But these approaches assume that features are independent and uniformly distributed. While this means that "why" explanations are correct, they may be longer than required. It also means the "why not" explanations may be suspect as the counterexamples they rely on may not be meaningful. In this paper, we show how one can apply background knowledge to give more succinct "why" formal explanations, that are presumably easier to interpret by humans, and give more accurate "why not" explanations. Furthermore, we also show how to use existing rule induction techniques to efficiently extract background information from a dataset, and also how to report which background information was used to make an explanation, allowing a human to examine it if they doubt the correctness of the explanation.

Related papers

• Dissenting Explanations: Leveraging Disagreement to Reduce Model Overreliance [4.962171160815189]
  We introduce the notion of dissenting explanations: conflicting predictions with accompanying explanations. We first explore the advantage of dissenting explanations in the setting of model multiplicity. We demonstrate that dissenting explanations reduce overreliance on model predictions, without reducing overall accuracy.
  arXiv  Detail & Related papers  (2023-07-14T21:27:00Z)
• Causal Explanations and XAI [8.909115457491522]
  An important goal of Explainable Artificial Intelligence (XAI) is to compensate for mismatches by offering explanations. I take a step further by formally defining the causal notions of sufficient explanations and counterfactual explanations. I also touch upon the significance of this work for fairness in AI by showing how actual causation can be used to improve the idea of path-specific counterfactual fairness.
  arXiv  Detail & Related papers  (2022-01-31T12:32:10Z)
• Human Interpretation of Saliency-based Explanation Over Text [65.29015910991261]
  We study saliency-based explanations over textual data. We find that people often mis-interpret the explanations. We propose a method to adjust saliencies based on model estimates of over- and under-perception.
  arXiv  Detail & Related papers  (2022-01-27T15:20:32Z)
• Diagnosing AI Explanation Methods with Folk Concepts of Behavior [70.10183435379162]
  We consider "success" to depend not only on what information the explanation contains, but also on what information the human explainee understands from it. We use folk concepts of behavior as a framework of social attribution by the human explainee.
  arXiv  Detail & Related papers  (2022-01-27T00:19:41Z)
• On Relating 'Why?' and 'Why Not?' Explanations [28.87208020322193]
  Explanations of Machine Learning (ML) models often address a 'Why?' question. Recent work has investigated explanations that address a 'Why Not?' question. This paper establishes a rigorous formal relationship between 'Why?' and 'Why Not?' explanations.
  arXiv  Detail & Related papers  (2020-12-21T01:07:13Z)
• Towards Interpretable Natural Language Understanding with Explanations as Latent Variables [146.83882632854485]
  We develop a framework for interpretable natural language understanding that requires only a small set of human annotated explanations for training. Our framework treats natural language explanations as latent variables that model the underlying reasoning process of a neural model.
  arXiv  Detail & Related papers  (2020-10-24T02:05:56Z)
• Explainable AI without Interpretable Model [0.0]
  It has become more important than ever that AI systems would be able to explain the reasoning behind their results to end-users. Most Explainable AI (XAI) methods are based on extracting an interpretable model that can be used for producing explanations. The notions of Contextual Importance and Utility (CIU) presented in this paper make it possible to produce human-like explanations of black-box outcomes directly.
  arXiv  Detail & Related papers  (2020-09-29T13:29:44Z)
• The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets [61.66584140190247]
  We show that feature-based explanations pose problems even for explaining trivial models. We show that two popular classes of explainers, Shapley explainers and minimal sufficient subsets explainers, target fundamentally different types of ground-truth explanations.
  arXiv  Detail & Related papers  (2020-09-23T09:45:23Z)
• An Information-Theoretic Approach to Personalized Explainable Machine Learning [92.53970625312665]
  We propose a simple probabilistic model for the predictions and user knowledge. We quantify the effect of an explanation by the conditional mutual information between the explanation and prediction.
  arXiv  Detail & Related papers  (2020-03-01T13:06:29Z)
• Adequate and fair explanations [12.33259114006129]
  We focus upon the second school of exact explanations with a rigorous logical foundation. With counterfactual explanations, many of the assumptions needed to provide a complete explanation are left implicit. We explore how to move from local partial explanations to what we call complete local explanations and then to global ones.
  arXiv  Detail & Related papers  (2020-01-21T14:42:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.