Alessandro, Facchini and Alberto, Termine (2021) Towards a Taxonomy of Pragmatic Opacity. [Preprint]

Preview

Text Taxonomy of Pragmatic Opacity.pdf Download (150kB) | Preview

Abstract

The research program of eXplainable AI (XAI) has been developed with the aim of providing tools and methods for reducing opacity and making AI systems more humanly understandable. Unfortunately, the majority of XAI scholars actually classify a system as more or less opaque by confronting it with traditional rules-based systems, which are usually assumed to be the prototype of transparent systems. In doing so, the concept of opacity remains unexplained. To overcome this issue, we propose to view opacity as a pragmatic concept. Based on this, we then explicit the distinction between structural opacity, link opacity and informational opacity, hence providing the groundwork for a conceptual taxonomy for XAI scholars and their practice

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Alessandro, Facchini alessandro.facchini@idisa.ch Alberto, Termine alberto.termine@unimi.it
Keywords:	Opacity, Explainable AI, Machine Learning, Scientific Understanding
Subjects:	General Issues > Data General Issues > Computer Simulation General Issues > Models and Idealization General Issues > Technology General Issues > Values In Science
Depositing User:	Mr. Alberto Termine
Date Deposited:	22 Oct 2021 04:23
Last Modified:	22 Oct 2021 04:23
Item ID:	19713
Subjects:	General Issues > Data General Issues > Computer Simulation General Issues > Models and Idealization General Issues > Technology General Issues > Values In Science
Date:	July 2021
URI:	https://philsci-archive.pitt.edu/id/eprint/19713

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item