Formalizing value-guided argumentation for ethical systems design

Abstract

The persuasiveness of an argument depends on the values promoted and demoted by the position defended. This idea, inspired by Perelman's work on argumentation, has become a prominent theme in artificial intelligence research on argumentation since the work by Hafner and Berman on teleological reasoning in the law, and was further developed by Bench-Capon in his value-based argumentation frameworks. One theme in the study of value-guided argumentation is the comparison of values. Formal models involving value comparison typically use either qualitative or quantitative primitives. In this paper, techniques connecting qualitative and quantitative primitives recently developed for evidential argumentation are applied to value-guided argumentation. By developing the theoretical understanding of intelligent systems guided by embedded values, the paper is a step towards ethical systems design, much needed in these days of ever more pervasive AI techniques.

Proof with and without probabilities

“…the paper 'To Catch A Thief With and Without Numbers'; Verheij 2014b). The mathematics of the formalism is studied further in Verheij (2016a) and has been applied to value-guided decision making in Verheij (2016c).…”

“…See Verheij (2016a) for further formal information. Nonformal differences are that the present proposal is designed to be a balance between qualitative and quantitative modeling, and has been applied to the modeling of evidential reasoning (this paper) and normative reasoning (Verheij 2016c). Kohlas et al (1998) proposes a probabilistic approach to model-based diagnostics using arguments supporting hypotheses about the state of a system.…”

Artificial Intelligence Regulation: A Meta-Framework for Formulation and Governance

“…Despite the small number of existing softwarebased regulation models, similar models are likely to arise, since the increasing complexity of AI solutions results in more system rules [51][52][53] [54], which in turn means a higher probability of conflicts between those rules in combined systems [55]. A problem, therefore, that exceeds the human capacity to follow.…”

HYPO’S legacy: introduction to the virtual special issue

“…The most recent work in this strand is Grabmair (2017). Finally, another approach to using values in the representation of cases can be found in Verheij (2016).…”