"Over-the-Hood" AI Inclusivity Bugs and How 3 AI Product Teams Found and Fixed Them

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Anderson, Andrew, Moussaoui, Fatima A., Guevara, Jimena Noa, Hamid, Md Montaser, Burnett, Margaret
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909863192297472
author Anderson, Andrew
Moussaoui, Fatima A.
Guevara, Jimena Noa
Hamid, Md Montaser
Burnett, Margaret
author_facet Anderson, Andrew
Moussaoui, Fatima A.
Guevara, Jimena Noa
Hamid, Md Montaser
Burnett, Margaret
contents While much research has shown the presence of AI's "under-the-hood" biases (e.g., algorithmic, training data, etc.), what about "over-the-hood" inclusivity biases: barriers in user-facing AI products that disproportionately exclude users with certain problem-solving approaches? Recent research has begun to report the existence of such biases -- but what do they look like, how prevalent are they, and how can developers find and fix them? To find out, we conducted a field study with 3 AI product teams, to investigate what kinds of AI inclusivity bugs exist uniquely in user-facing AI products, and whether/how AI product teams might harness an existing (non-AI-oriented) inclusive design method to find and fix them. The teams' work resulted in identifying 6 types of AI inclusivity bugs arising 83 times, fixes covering 47 of these bug instances, and a new variation of the GenderMag inclusive design method, GenderMag-for-AI, that is especially effective at detecting certain kinds of AI inclusivity bugs.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19033
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle "Over-the-Hood" AI Inclusivity Bugs and How 3 AI Product Teams Found and Fixed Them
Anderson, Andrew
Moussaoui, Fatima A.
Guevara, Jimena Noa
Hamid, Md Montaser
Burnett, Margaret
Human-Computer Interaction
Artificial Intelligence
While much research has shown the presence of AI's "under-the-hood" biases (e.g., algorithmic, training data, etc.), what about "over-the-hood" inclusivity biases: barriers in user-facing AI products that disproportionately exclude users with certain problem-solving approaches? Recent research has begun to report the existence of such biases -- but what do they look like, how prevalent are they, and how can developers find and fix them? To find out, we conducted a field study with 3 AI product teams, to investigate what kinds of AI inclusivity bugs exist uniquely in user-facing AI products, and whether/how AI product teams might harness an existing (non-AI-oriented) inclusive design method to find and fix them. The teams' work resulted in identifying 6 types of AI inclusivity bugs arising 83 times, fixes covering 47 of these bug instances, and a new variation of the GenderMag inclusive design method, GenderMag-for-AI, that is especially effective at detecting certain kinds of AI inclusivity bugs.
title "Over-the-Hood" AI Inclusivity Bugs and How 3 AI Product Teams Found and Fixed Them
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2510.19033