Explaining Explanations in AI

FAT* 2019 Proceedings 1 (forthcoming)
  Copy   BIBTEX

Abstract

Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained professionals how to predict what decisions will be made by the complex system, and most importantly how the system might break. However, when considering any such model it’s important to remember Box’s maxim that "All models are wrong but some are useful." We focus on the distinction between these models and explanations in philosophy and sociology. These models can be understood as a "do it yourself kit" for explanations, allowing a practitioner to directly answer "what if questions" or generate contrastive explanations without external assistance. Although a valuable ability, giving these models as explanations appears more difficult than necessary, and other forms of explanation may not have the same trade-offs. We contrast the different schools of thought on what makes an explanation, and suggest that machine learning might benefit from viewing the problem more broadly.

Other Versions

No versions found

Links

PhilArchive

External links

  • This entry has no external links. Add one.
Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

Similar books and articles

What is psychological explanation?William Bechtel & Cory Wright - 2009 - In Sarah Robins, John Symons & Paco Calvo (eds.), The Routledge Companion to Philosophy of Psychology. New York, NY: Routledge. pp. 113--130.
Models and Explanation.Alisa Bokulich - 2017 - In Magnani Lorenzo & Bertolotti Tommaso Wayne (eds.), Springer Handbook of Model-Based Science. Springer. pp. 103-118.
Opacity, Machine Learning and Explainable AI.Alberto Fernández - 2023 - In Francisco Lara & Jan Deckers (eds.), Ethics of Artificial Intelligence. Springer Nature Switzerland. pp. 39-58.
Causal Explanations and XAI.Sander Beckers - 2022 - Proceedings of the 1St Conference on Causal Learning and Reasoning, Pmlr.
Model Explanation Versus Model-Induced Explanation.Insa Lawler & Emily Sullivan - 2021 - Foundations of Science 26 (4):1049-1074.
Evaluating Explanations: A Content Theory.David B. Leake - 1992 - Hillsdale, NJ: Lawrence Erlbaum.

Analytics

Added to PP
2018-11-04

Downloads
1,476 (#8,847)

6 months
183 (#22,852)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Brent Mittelstadt
University of Oxford

References found in this work

Counterfactuals.David K. Lewis - 1973 - Malden, Mass.: Blackwell.
Counterfactuals.David Lewis - 1973 - Foundations of Language 13 (1):145-151.
Models and Analogies in Science.Mary Hesse - 1965 - British Journal for the Philosophy of Science 16 (62):161-163.
Models and Analogies in Science.Mary B. Hesse - 1966 - Philosophy and Rhetoric 3 (3):190-191.

View all 25 references / Add more references