Explainability Through Systematicity: The Hard Systematicity Challenge for Artificial Intelligence

TL;DR

This paper explores the concept of systematicity in AI, arguing that a richer, more integrated notion of systematicity is essential for understanding AI's rationality and explainability beyond traditional connectionist views.

Contribution

It introduces a conceptual framework for systematicity, distinguishes four senses of the term, and applies this to evaluate the rationales for systematization in AI.

Findings

Distinguishes four senses of systematicity in thought.

Reframes the systematicity challenge in connectionist AI.

Proposes a dynamic regulation of systematicity based on rationales.

Abstract

This paper argues that explainability is only one facet of a broader ideal that shapes our expectations towards artificial intelligence (AI). Fundamentally, the issue is to what extent AI exhibits systematicity--not merely in being sensitive to how thoughts are composed of recombinable constituents, but in striving towards an integrated body of thought that is consistent, coherent, comprehensive, and parsimoniously principled. This richer conception of systematicity has been obscured by the long shadow of the "systematicity challenge" to connectionism, according to which network architectures are fundamentally at odds with what Fodor and colleagues termed "the systematicity of thought." I offer a conceptual framework for thinking about "the systematicity of thought" that distinguishes four senses of the phrase. I use these distinctions to defuse the perceived tension between systematicity and connectionism and show that the conception of systematicity that historically shaped our sense of what makes thought rational, authoritative, and scientific is more demanding than the Fodorian notion. To determine whether we have reason to hold AI models to this ideal of systematicity, I then argue, we must look to the rationales for systematization and explore to what extent they transfer to AI models. I identify five such rationales and apply them to AI. This brings into view the "hard systematicity challenge." However, the demand for systematization itself needs to be regulated by the rationales for systematization. This yields a dynamic understanding of the need to systematize thought, which tells us how systematic we need AI models to be and when.