Cookies?
Library Header Image
LSE Research Online LSE Library Services

A new paradigm for counterfactual reasoning in fairness and recourse

Bynum, Lucius E.J., Loftus, Joshua R. ORCID: 0000-0002-2905-1632 and Stoyanovich, Julia (2024) A new paradigm for counterfactual reasoning in fairness and recourse. In: Larson, Kate, (ed.) Proceedings of the 33rd International Joint Conference on Artificial Intelligence, IJCAI 2024. IJCAI International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence, pp. 7092-7100. ISBN 9781956792041

Full text not available from this repository.

Abstract

Counterfactuals underpin numerous techniques for auditing and understanding artificial intelligence (AI) systems. The traditional paradigm for counterfactual reasoning in this literature is the interventional counterfactual, where hypothetical interventions are imagined and simulated. For this reason, the starting point for causal reasoning about legal protections and demographic data in AI is an imagined intervention on a legally-protected characteristic, such as ethnicity, race, gender, disability, age, etc. We ask, for example, what would have happened had your race been different? An inherent limitation of this paradigm is that some demographic interventions - like interventions on race - may not be well-defined or translate into the formalisms of interventional counterfactuals. In this work, we explore a new paradigm based instead on the backtracking counterfactual, where rather than imagine hypothetical interventions on legally-protected characteristics, we imagine alternate initial conditions while holding these characteristics fixed. We ask instead, what would explain a counterfactual outcome for you as you actually are or could be? This alternate framework allows us to address many of the same social concerns, but to do so while asking fundamentally different questions that do not rely on demographic interventions.

Item Type: Book Section
Additional Information: © 2024 International Joint Conferences on Artificial Intelligence.
Divisions: Statistics
LSE
Subjects: H Social Sciences > HA Statistics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Date Deposited: 02 Oct 2024 09:12
Last Modified: 06 Nov 2024 20:30
URI: http://eprints.lse.ac.uk/id/eprint/125591

Actions (login required)

View Item View Item