Importance of User Control in Data-Centric Steering for Healthcare Experts

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Bhattacharya, Aditya, Stumpf, Simone, Verbert, Katrien
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909657538232320
author Bhattacharya, Aditya
Stumpf, Simone
Verbert, Katrien
author_facet Bhattacharya, Aditya
Stumpf, Simone
Verbert, Katrien
contents As Artificial Intelligence (AI) becomes increasingly integrated into high-stakes domains like healthcare, effective collaboration between healthcare experts and AI systems is critical. Data-centric steering, which involves fine-tuning prediction models by improving training data quality, plays a key role in this process. However, little research has explored how varying levels of user control affect healthcare experts during data-centric steering. We address this gap by examining manual and automated steering approaches through a between-subjects, mixed-methods user study with 74 healthcare experts. Our findings show that manual steering, which grants direct control over training data, significantly improves model performance while maintaining trust and system understandability. Based on these findings, we propose design implications for a hybrid steering system that combines manual and automated approaches to increase user involvement during human-AI collaboration.
format Preprint
id arxiv_https___arxiv_org_abs_2506_18770
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Importance of User Control in Data-Centric Steering for Healthcare Experts
Bhattacharya, Aditya
Stumpf, Simone
Verbert, Katrien
Human-Computer Interaction
As Artificial Intelligence (AI) becomes increasingly integrated into high-stakes domains like healthcare, effective collaboration between healthcare experts and AI systems is critical. Data-centric steering, which involves fine-tuning prediction models by improving training data quality, plays a key role in this process. However, little research has explored how varying levels of user control affect healthcare experts during data-centric steering. We address this gap by examining manual and automated steering approaches through a between-subjects, mixed-methods user study with 74 healthcare experts. Our findings show that manual steering, which grants direct control over training data, significantly improves model performance while maintaining trust and system understandability. Based on these findings, we propose design implications for a hybrid steering system that combines manual and automated approaches to increase user involvement during human-AI collaboration.
title Importance of User Control in Data-Centric Steering for Healthcare Experts
topic Human-Computer Interaction
url https://arxiv.org/abs/2506.18770