The Four Fundamental Components for Intelligibility and Interpretability in AI Ethics

American Philosophical Quarterly (forthcoming)
  Copy   BIBTEX

Abstract

Intelligibility and interpretability related to artificial intelligence (AI) are crucial for enabling explicability, which is vital for establishing constructive communication and agreement among various stakeholders, including users and designers of AI. It is essential to overcome the challenges of sharing an understanding of the details of the various structures of diverse AI systems, to facilitate effective communication and collaboration. In this paper, we propose four fundamental terms: “I/O,” “Constraints,” “Objectives,” and “Architecture.” These terms help mitigate the challenges associated with intelligibility and interpretability in AI by providing appropriate levels of abstraction to describe structure of AI systems generally, thereby facilitating the sharing of understanding among various stakeholders. The relationship between the Objective of AI designers and the Purpose of AI users is linked to the issues of AI alignment.

Links

PhilArchive

External links

  • This entry has no external links. Add one.
Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

Complexity of the interpretability logics ILW and ILP.Luka Mikec - 2023 - Logic Journal of the IGPL 31 (1):194-213.
Interpretability over peano arithmetic.Claes Strannegård - 1999 - Journal of Symbolic Logic 64 (4):1407-1425.
Interpretability over peano arithmetic.Claes Strannegård - 1999 - Journal of Symbolic Logic 64 (4):1407-1425.
Interpretability over peano arithmetic.Claes Strannegård - 1999 - Journal of Symbolic Logic 64 (4):1407-1425.
The formalization of interpretability.Albert Visser - 1991 - Studia Logica 50 (1):81 - 105.
Universal Gravitation and the (Un)Intelligibility of Natural Philosophy.Matias Slavov - 2019 - Pacific Philosophical Quarterly 101 (1):129-157.
Overdue analysis of Bourdieu's theory of practice.Theodore Richard Schatzki - 1987 - Inquiry: An Interdisciplinary Journal of Philosophy 30 (1 & 2):113 – 135.
Heidegger, Dreyfus, and the Intelligibility of Practical Comportment.Leslie A. MacAvoy - 2019 - Journal of the British Society for Phenomenology 50 (1):68-86.
Real Sparks of Artificial Intelligence and the Importance of Inner Interpretability.Alex Grzankowski - forthcoming - Inquiry: An Interdisciplinary Journal of Philosophy.

Analytics

Added to PP
2024-04-12

Downloads
110 (#161,790)

6 months
110 (#39,419)

Historical graph of downloads
How can I increase my downloads?