On the Injunction of XAIxArt

TL;DR

This position paper critiques the use of explainable AI in art, arguing it reflects insecurity in human-centric art notions and advocates for a shift from ornamentation explanations to sense-making models.

Contribution

It challenges the assumptions of explanation in XAIxArt and proposes a new perspective emphasizing sense-making over traditional explanation models.

Findings

XAIxArt reflects insecurity in anthropocentric art concepts

Current explanations are rooted in outdated notions of authorship

A shift towards sense-making models is proposed

Abstract

The position paper highlights the range of concerns that are engulfed in the injunction of explainable artificial intelligence in art (XAIxArt). Through a series of quick sub-questions, it points towards the ambiguities concerning 'explanation' and the postpositivist tradition of 'relevant explanation'. Rejecting both 'explanation' and 'relevant explanation', the paper takes a stance that XAIxArt is a symptom of insecurity of the anthropocentric notion of art and a nostalgic desire to return to outmoded notions of authorship and human agency. To justify this stance, the paper makes a distinction between an ornamentation model of explanation to a model of explanation as sense-making.