Rabiza, Marcin (2024) A Mechanistic Explanatory Strategy for XAI. [Preprint]
This is the latest version of this item.
Text
Rabiza - Mechanistic XAI (preprint).pdf - Accepted Version Available under License Creative Commons Attribution. Download (591kB) |
Abstract
Despite significant advancements in XAI, scholars note a persistent lack of solid conceptual foundations and integration with broader scientific discourse on explanation. In response, emerging XAI research draws on explanatory strategies from various sciences and philosophy of science literature to fill these gaps. This paper outlines a mechanistic strategy for explaining the functional organization of deep learning systems, situating recent advancements in AI explainability within a broader philosophical context. According to the mechanistic approach, the explanation of opaque AI systems involves identifying mechanisms that drive decision-making. For deep neural net-works, this means discerning functionally relevant components—such as neurons, layers, circuits, or activation patterns—and understanding their roles through decomposition, localization, and re-composition. Proof-of-principle case studies from image recognition and language modeling align these theoretical approaches with the latest research from AI labs like OpenAI and Anthropic. This research suggests that a systematic approach to studying model organization can reveal elements that simpler (or “more modest”) explainability techniques might miss, fostering more thoroughly explainable AI. The paper concludes with a discussion on the epistemic relevance of the mechanistic approach positioned in the context of selected philosophical debates on XAI.
Export/Citation: | EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL |
Social Networking: |
Available Versions of this Item
-
A Mechanistic Explanatory Strategy for XAI. (deposited 03 Nov 2024 12:48)
- A Mechanistic Explanatory Strategy for XAI. (deposited 03 Nov 2024 12:48) [Currently Displayed]
Monthly Views for the past 3 years
Monthly Downloads for the past 3 years
Plum Analytics
Actions (login required)
View Item |