Logic Is Not Enough: Why Reasoning About Another Person’s Beliefs Is Reasoning Under Uncertainty

By Anthony Jameson (1995)

In A. Laux & H. Wansing (Hrsg.), Knowledge and belief in philosophy and artificial intelligence (S. 199–229). Berlin: Akademie Verlag.

Abstract

A system that reasons about the beliefs of a person must in general be able to ascribe a good deal of general background knowledge to that person, often in the absence of reliable evidence that the person possesses that knowledge. In some cases it is possible to make the necessary inferences within a logical framework, often as default inferences, using as premises information about the person’s membership in some group or information about the system’s own knowledge. But these approaches do not in general adequately deal with the uncertainty that pervades the ascription of general background knowledge. An explicitly probabilistic framework, intuitive psychometrics, was developed to provide a more adequate normative and descriptive account of this ascription process. Implemented using Bayesian networks, intuitive psychometrics can be used in conjunction with a modal-logic-based system for epistemic reasoning, so that the power of both the logical and the probabilistic approaches can be exploited.

Download

Full Publication:  

BibTeX entry

@incollection{Jameson95,
  year = {1995},
  author = {{Jameson}, Anthony},
  editor = {{Laux}, Armin and
            {Wansing}, Heinrich},
  title = {Logic Is Not Enough: Why Reasoning About Another Person’s Beliefs Is Reasoning Under Uncertainty},
  booktitle = {Knowledge and Belief in Philosophy and Artificial Intelligence},
  address = {Berlin},
  publisher = {Akademie Verlag},
  pages = {199--229}}