Modeling Discrimination with Causal Abstraction

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Mossé, Milan, Schechtman, Kara, Eberhardt, Frederick, Icard, Thomas
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909745926897664
author Mossé, Milan
Schechtman, Kara
Eberhardt, Frederick
Icard, Thomas
author_facet Mossé, Milan
Schechtman, Kara
Eberhardt, Frederick
Icard, Thomas
contents A person is directly racially discriminated against only if her race caused her worse treatment. This implies that race is an attribute sufficiently separable from other attributes to isolate its causal role. But race is embedded in a nexus of social factors that resist isolated treatment. If race is socially constructed, in what sense can it cause worse treatment? Some propose that the perception of race, rather than race itself, causes worse treatment. Others suggest that since causal models require \textit{modularity}, i.e. the ability to isolate causal effects, attempts to causally model discrimination are misguided. This paper addresses the problem differently. We introduce a framework for reasoning about discrimination, in which race is a high-level \textit{abstraction} of lower-level features. In this framework, race can be modeled as itself causing worse treatment. Modularity is ensured by allowing assumptions about social construction to be precisely and explicitly stated, via an alignment between race and its constituents. Such assumptions can then be subjected to normative and empirical challenges, which lead to different views of when discrimination occurs. By distinguishing constitutive and causal relations, the abstraction framework pinpoints disagreements in the current literature on modeling discrimination, while preserving a precise causal account of discrimination.
format Preprint
id arxiv_https___arxiv_org_abs_2501_08429
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Modeling Discrimination with Causal Abstraction
Mossé, Milan
Schechtman, Kara
Eberhardt, Frederick
Icard, Thomas
Computers and Society
Artificial Intelligence
A person is directly racially discriminated against only if her race caused her worse treatment. This implies that race is an attribute sufficiently separable from other attributes to isolate its causal role. But race is embedded in a nexus of social factors that resist isolated treatment. If race is socially constructed, in what sense can it cause worse treatment? Some propose that the perception of race, rather than race itself, causes worse treatment. Others suggest that since causal models require \textit{modularity}, i.e. the ability to isolate causal effects, attempts to causally model discrimination are misguided. This paper addresses the problem differently. We introduce a framework for reasoning about discrimination, in which race is a high-level \textit{abstraction} of lower-level features. In this framework, race can be modeled as itself causing worse treatment. Modularity is ensured by allowing assumptions about social construction to be precisely and explicitly stated, via an alignment between race and its constituents. Such assumptions can then be subjected to normative and empirical challenges, which lead to different views of when discrimination occurs. By distinguishing constitutive and causal relations, the abstraction framework pinpoints disagreements in the current literature on modeling discrimination, while preserving a precise causal account of discrimination.
title Modeling Discrimination with Causal Abstraction
topic Computers and Society
Artificial Intelligence
url https://arxiv.org/abs/2501.08429