Saved in:
Bibliographic Details
Main Authors: Levonian, Zachary, Hagen, Lauren, Li, Lu, Lilleboe, Jada, Wastvedt, Solvejg, Halfaker, Aaron, Terveen, Loren
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.08453
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916283883192320
author Levonian, Zachary
Hagen, Lauren
Li, Lu
Lilleboe, Jada
Wastvedt, Solvejg
Halfaker, Aaron
Terveen, Loren
author_facet Levonian, Zachary
Hagen, Lauren
Li, Lu
Lilleboe, Jada
Wastvedt, Solvejg
Halfaker, Aaron
Terveen, Loren
contents Auditing the machine learning (ML) models used on Wikipedia is important for ensuring that vandalism-detection processes remain fair and effective. However, conducting audits is challenging because stakeholders have diverse priorities and assembling evidence for a model's [in]efficacy is technically complex. We designed an interface to enable editors to learn about and audit the performance of the ORES edit quality model. ORES-Inspect is an open-source web tool and a provocative technology probe for researching how editors think about auditing the many ML models used on Wikipedia. We describe the design of ORES-Inspect and our plans for further research with this system.
format Preprint
id arxiv_https___arxiv_org_abs_2406_08453
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ORES-Inspect: A technology probe for machine learning audits on enwiki
Levonian, Zachary
Hagen, Lauren
Li, Lu
Lilleboe, Jada
Wastvedt, Solvejg
Halfaker, Aaron
Terveen, Loren
Human-Computer Interaction
K.4.2
Auditing the machine learning (ML) models used on Wikipedia is important for ensuring that vandalism-detection processes remain fair and effective. However, conducting audits is challenging because stakeholders have diverse priorities and assembling evidence for a model's [in]efficacy is technically complex. We designed an interface to enable editors to learn about and audit the performance of the ORES edit quality model. ORES-Inspect is an open-source web tool and a provocative technology probe for researching how editors think about auditing the many ML models used on Wikipedia. We describe the design of ORES-Inspect and our plans for further research with this system.
title ORES-Inspect: A technology probe for machine learning audits on enwiki
topic Human-Computer Interaction
K.4.2
url https://arxiv.org/abs/2406.08453