Quantifying Query Fairness Under Unawareness

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Jaenich, Thomas, Moreo, Alejandro, Fabris, Alessandro, McDonald, Graham, Esuli, Andrea, Ounis, Iadh, Sebastiani, Fabrizio
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908393568993280
author Jaenich, Thomas
Moreo, Alejandro
Fabris, Alessandro
McDonald, Graham
Esuli, Andrea
Ounis, Iadh
Sebastiani, Fabrizio
author_facet Jaenich, Thomas
Moreo, Alejandro
Fabris, Alessandro
McDonald, Graham
Esuli, Andrea
Ounis, Iadh
Sebastiani, Fabrizio
contents Traditional ranking algorithms are designed to retrieve the most relevant items for a user's query, but they often inherit biases from data that can unfairly disadvantage vulnerable groups. Fairness in information access systems (IAS) is typically assessed by comparing the distribution of groups in a ranking to a target distribution, such as the overall group distribution in the dataset. These fairness metrics depend on knowing the true group labels for each item. However, when groups are defined by demographic or sensitive attributes, these labels are often unknown, leading to a setting known as "fairness under unawareness". To address this, group membership can be inferred using machine-learned classifiers, and group prevalence is estimated by counting the predicted labels. Unfortunately, such an estimation is known to be unreliable under dataset shift, compromising the accuracy of fairness evaluations. In this paper, we introduce a robust fairness estimator based on quantification that effectively handles multiple sensitive attributes beyond binary classifications. Our method outperforms existing baselines across various sensitive attributes and, to the best of our knowledge, is the first to establish a reliable protocol for measuring fairness under unawareness across multiple queries and groups.
format Preprint
id arxiv_https___arxiv_org_abs_2506_04140
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantifying Query Fairness Under Unawareness
Jaenich, Thomas
Moreo, Alejandro
Fabris, Alessandro
McDonald, Graham
Esuli, Andrea
Ounis, Iadh
Sebastiani, Fabrizio
Information Retrieval
Traditional ranking algorithms are designed to retrieve the most relevant items for a user's query, but they often inherit biases from data that can unfairly disadvantage vulnerable groups. Fairness in information access systems (IAS) is typically assessed by comparing the distribution of groups in a ranking to a target distribution, such as the overall group distribution in the dataset. These fairness metrics depend on knowing the true group labels for each item. However, when groups are defined by demographic or sensitive attributes, these labels are often unknown, leading to a setting known as "fairness under unawareness". To address this, group membership can be inferred using machine-learned classifiers, and group prevalence is estimated by counting the predicted labels. Unfortunately, such an estimation is known to be unreliable under dataset shift, compromising the accuracy of fairness evaluations. In this paper, we introduce a robust fairness estimator based on quantification that effectively handles multiple sensitive attributes beyond binary classifications. Our method outperforms existing baselines across various sensitive attributes and, to the best of our knowledge, is the first to establish a reliable protocol for measuring fairness under unawareness across multiple queries and groups.
title Quantifying Query Fairness Under Unawareness
topic Information Retrieval
url https://arxiv.org/abs/2506.04140