Emergent, not Immanent: A Baradian Reading of Explainable AI

TL;DR

This paper challenges traditional views of explainable AI by applying Barad's agential realism, emphasizing interpretative performances emerging from entanglements rather than static explanations, and proposes new design directions.

Contribution

It introduces an agential realism framework to understand XAI as emergent, material-discursive performances, revealing underlying assumptions and ethical considerations.

Findings

Revealed limitations of existing XAI methods through agential realism analysis.

Proposed a new interpretative framework emphasizing emergent, situated performances.

Illustrated design implications with a case study on a text-to-music interface.

Abstract

Explainable AI (XAI) is frequently positioned as a technical problem of revealing the inner workings of an AI model. This position is affected by unexamined onto-epistemological assumptions: meaning is treated as immanent to the model, the explainer is positioned outside the system, and a causal structure is presumed recoverable through computational techniques. In this paper, we draw on Barad's agential realism to develop an alternative onto-epistemology of XAI. We propose that interpretations are material-discursive performances that emerge from situated entanglements of the AI model with humans, context, and the interpretative apparatus. To develop this position, we read a comprehensive set of XAI methods through agential realism and reveal the assumptions and limitations that underpin several of these methods. We then articulate the framework's ethical dimension and propose design directions for XAI interfaces that support emergent interpretation, using a speculative text-to-music interface as a case study.