PhilSci Archive

Variation semantics: when counterfactuals in explanations of algorithmic decisions are true

Hudetz, Laurenz and Crawford, Neil (2022) Variation semantics: when counterfactuals in explanations of algorithmic decisions are true. [Preprint]

[img]
Preview
Text
Counterfactuals 2022-03-14.pdf

Download (459kB) | Preview

Abstract

We propose a new semantics for counterfactual conditionals. It is primarily motivated by the need for an adequate framework for evaluating counterfactual explanations of algorithmic decisions. We argue that orthodox Lewis-Stalnaker similarity semantics and interventionist causal modelling semantics are not adequate frameworks because they classify too many counterfactuals as true. Our proposed semantics overcomes this problem of the orthodox approaches and has further advantages, including simplicity, robustness, closeness to practice and applicability. It is based on the idea that a counterfactual `if A were the case, C would be the case' is true at an elementary possibility ω just in case C is true at all variants of ω at which A is true, other things being equal. We provide a novel explication of the idea of a variation that makes a given sentence true while leaving other things (but not necessarily all other things) equal.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Hudetz, Laurenzl.hudetz@lse.ac.uk
Crawford, Neilneilsc@uci.edu
Keywords: counterfactual conditionals; counterfactual explanation; algorithmic decisions; machine learning; truth conditions;
Subjects: Specific Sciences > Mathematics > Logic
Specific Sciences > Computer Science
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
Depositing User: Dr Laurenz Hudetz
Date Deposited: 18 May 2022 13:29
Last Modified: 18 May 2022 13:29
Item ID: 20626
Subjects: Specific Sciences > Mathematics > Logic
Specific Sciences > Computer Science
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
Date: 2022
URI: https://philsci-archive.pitt.edu/id/eprint/20626

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item