The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Goyal, Navita, Baumler, Connor, Nguyen, Tin, Daumé III, Hal
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916198121209856
author Goyal, Navita
Baumler, Connor
Nguyen, Tin
Daumé III, Hal
author_facet Goyal, Navita
Baumler, Connor
Nguyen, Tin
Daumé III, Hal
contents AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against some protected group, explanations may include features that demonstrate this bias, but when biases are realized through proxy features, the relationship between this proxy feature and the protected one may be less clear to a human. In this work, we study the effect of the presence of protected and proxy features on participants' perception of model fairness and their ability to improve demographic parity over an AI alone. Further, we examine how different treatments -- explanations, model bias disclosure and proxy correlation disclosure -- affect fairness perception and parity. We find that explanations help people detect direct but not indirect biases. Additionally, regardless of bias type, explanations tend to increase agreement with model biases. Disclosures can help mitigate this effect for indirect biases, improving both unfairness recognition and decision-making fairness. We hope that our findings can help guide further research into advancing explanations in support of fair human-AI decision-making.
format Preprint
id arxiv_https___arxiv_org_abs_2310_08617
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features
Goyal, Navita
Baumler, Connor
Nguyen, Tin
Daumé III, Hal
Artificial Intelligence
Human-Computer Interaction
AI systems have been known to amplify biases in real-world data. Explanations may help human-AI teams address these biases for fairer decision-making. Typically, explanations focus on salient input features. If a model is biased against some protected group, explanations may include features that demonstrate this bias, but when biases are realized through proxy features, the relationship between this proxy feature and the protected one may be less clear to a human. In this work, we study the effect of the presence of protected and proxy features on participants' perception of model fairness and their ability to improve demographic parity over an AI alone. Further, we examine how different treatments -- explanations, model bias disclosure and proxy correlation disclosure -- affect fairness perception and parity. We find that explanations help people detect direct but not indirect biases. Additionally, regardless of bias type, explanations tend to increase agreement with model biases. Disclosures can help mitigate this effect for indirect biases, improving both unfairness recognition and decision-making fairness. We hope that our findings can help guide further research into advancing explanations in support of fair human-AI decision-making.
title The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features
topic Artificial Intelligence
Human-Computer Interaction
url https://arxiv.org/abs/2310.08617