• Corpus ID: 222067026

Explaining AI as an Exploratory Process: The Peircean Abduction Model

  title={Explaining AI as an Exploratory Process: The Peircean Abduction Model},
  author={Robert R. Hoffman and William J. Clancey and Shane T. Mueller},
Current discussions of "Explainable AI" (XAI) do not much consider the role of abduction in explanatory reasoning (see Mueller, et al., 2018). It might be worthwhile to pursue this, to develop intelligent systems that allow for the observation and analysis of abductive reasoning and the assessment of abductive reasoning as a learnable skill. Abductive inference has been defined in many ways. For example, it has been defined as the achievement of insight. Most often abduction is taken as a… 
1 Citations

Tables from this paper

Diagnosing AI Explanation Methods with Folk Concepts of Behavior
When explaining AI behavior to humans, how is the communicated information being comprehended by the human explainee, and does it match what the explanation attempted to communicate? When can we say


Abductive Reasoning: Challenges Ahead
The motivation behind the collection of papers presented in this THEORIA forum on Abductive reasoning is my book Abductive Reasoning: Logical Investigations into the Processes of Discovery and
Patterns of abduction
Several kinds of creative abductions are introduced, such as theoretical model abduction, common cause abduction and statistical factor analysis, and the article illustrates them by various real case examples.
The Extraordinary Ordinary Powers of Abductive Reasoning
The psychology of cognition has been influenced by semiotic models of representation, but little work has been done relating semiotics and the process of cognition proper. In this paper, I argue that
Integrating Abduction and Induction in Machine Learning
This chapter reviews the work in induction and abduction, which has developed methods for using abduction to identify faults and suggest repairs for theory refinement, and for inducing knowledge bases for abductive diagnosis from a database of expert-diagnosed cases.
"Theoric Transformations" and a New Classification of Abductive Inferences
Based on a definition of "abductive insight" and a critical discussion of G. Schurz's (2008) distinction of eleven "patterns of abduction" that he organizes in four groups, I suggest an even more
Diagrams as Scaffolds for Abductive Insights
  • M. Hoffmann
  • Philosophy
    Visual Representations and Reasoning
  • 2010
My thesis is, first, that the argumentative structure of the pursued problem solution guides abductive creativity and, second, that diagrammatic reasoning--if conceptualized according to the requirements defined by Charles Peirce--can support this guidance.
Abductive reasoning in multiple fault diagnosis
This paper focuses on the use of abductive reasoning in diagnostic systems in which there may be more than one underlying cause for the observed symptoms, and reviews and compares several different approaches, including Binary Choice Bayesian, SequentialBayesian, Causal Model Based Abduction, Parsimonious Set Covering and First Order Logic.
A prolog-like inference system for computing minimum-cost abductive explanations in natural-language interpretation
  • M. Stickel
  • Computer Science
    Annals of Mathematics and Artificial Intelligence
  • 2005
A new form of abduction — least specific abduction — is proposed as being more appropriate to the task of interpreting natural language than the forms that have been used in the traditional diagnostic and design-synthesis applications of abduction.
Explanation and Abductive Inference
Everyday cognition reveals a sophisticated capacity to seek, generate, and evaluate explanations for the social and physical worlds around us. Why are we so driven to explain, and what accounts for
The Computational Complexity of Abduction