"What Is It That You Don't Understand?" Language Games and Black Box Algorithms

TL;DR

This paper explores the inherent limitations of interpretability in black box algorithms, emphasizing the philosophical challenges of understanding AI models through language games and partial explanations.

Contribution

It highlights the importance of interpretability over explainability and draws parallels with linguistic philosophy to explain the inscrutability of AI models.

Findings

Complete explicability of algorithms is unattainable.

Interpretability is limited by the inscrutability of reference.

Language games shape the understanding of AI models.

Abstract

The aim of this article is to understand the problem of "black box" algorithms, an issue inherent to the nascent field of Explainable Artificial Intelligence (XAI). While it is relatively easy to understand something someone explained to us, it becomes more complicated when no one can fully grasp the issue. Our purpose is however to highlight: (1) that we should speak of interpretability rather than explainability when we seek to understand models, mainly because we never have complete and unambiguous access to information; (2) that the machines face the problem of the inscrutability of reference, in the same way that the linguist imagined by Willard Van Orman Quine cannot precisely determine what the term "gavagai" refers to in a situation of radical translation; (3) that there is no rule for the application of language, except for "language games", as Ludwig Wittgenstein's linguistics teaches us. The hope of achieving complete explicability and transparency of algorithms is undoubtedly in vain: we can only rely on partial and broad interpretations that will never fully explain the underlying rules.