Counterfactual Generation with Answer Set Programming

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dasgupta, Sopam, Shakerin, Farhad, Arias, Joaquín, Salazar, Elmer, Gupta, Gopal
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914669801766912
author Dasgupta, Sopam
Shakerin, Farhad
Arias, Joaquín
Salazar, Elmer
Gupta, Gopal
author_facet Dasgupta, Sopam
Shakerin, Farhad
Arias, Joaquín
Salazar, Elmer
Gupta, Gopal
contents Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail approval, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they are unable to reveal how they reach these prediction decisions. A need for transparency demands justification for such predictions. An affected individual might also desire explanations to understand why a decision was made. Ethical and legal considerations may further require informing the individual of changes in the input attribute that could be made to produce a desirable outcome. This paper focuses on the latter problem of automatically generating counterfactual explanations. We propose a framework Counterfactual Generation with s(CASP) (CFGS) that utilizes answer set programming (ASP) and the s(CASP) goal-directed ASP system to automatically generate counterfactual explanations from rules generated by rule-based machine learning (RBML) algorithms. In our framework, we show how counterfactual explanations are computed and justified by imagining worlds where some or all factual assumptions are altered/changed. More importantly, we show how we can navigate between these worlds, namely, go from our original world/scenario where we obtain an undesired outcome to the imagined world/scenario where we obtain a desired/favourable outcome.
format Preprint
id arxiv_https___arxiv_org_abs_2402_04382
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Counterfactual Generation with Answer Set Programming
Dasgupta, Sopam
Shakerin, Farhad
Arias, Joaquín
Salazar, Elmer
Gupta, Gopal
Artificial Intelligence
Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail approval, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they are unable to reveal how they reach these prediction decisions. A need for transparency demands justification for such predictions. An affected individual might also desire explanations to understand why a decision was made. Ethical and legal considerations may further require informing the individual of changes in the input attribute that could be made to produce a desirable outcome. This paper focuses on the latter problem of automatically generating counterfactual explanations. We propose a framework Counterfactual Generation with s(CASP) (CFGS) that utilizes answer set programming (ASP) and the s(CASP) goal-directed ASP system to automatically generate counterfactual explanations from rules generated by rule-based machine learning (RBML) algorithms. In our framework, we show how counterfactual explanations are computed and justified by imagining worlds where some or all factual assumptions are altered/changed. More importantly, we show how we can navigate between these worlds, namely, go from our original world/scenario where we obtain an undesired outcome to the imagined world/scenario where we obtain a desired/favourable outcome.
title Counterfactual Generation with Answer Set Programming
topic Artificial Intelligence
url https://arxiv.org/abs/2402.04382