Underspecified Human Decision Experiments Considered Harmful

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hullman, Jessica, Kale, Alex, Hartline, Jason
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918006273081344
author Hullman, Jessica
Kale, Alex
Hartline, Jason
author_facet Hullman, Jessica
Kale, Alex
Hartline, Jason
contents Decision-making with information displays is a key focus of research in areas like human-AI collaboration and data visualization. However, what constitutes a decision problem, and what is required for an experiment to conclude that decisions are flawed, remain imprecise. We present a widely applicable definition of a decision problem synthesized from statistical decision theory and information economics. We claim that to attribute loss in human performance to bias, an experiment must provide the information that a rational agent would need to identify the normative decision. We evaluate whether recent empirical research on AI-assisted decisions achieves this standard. We find that only 10 (26%) of 39 studies that claim to identify biased behavior presented participants with sufficient information to make this claim in at least one treatment condition. We motivate the value of studying well-defined decision problems by describing a characterization of performance losses they allow to be conceived.
format Preprint
id arxiv_https___arxiv_org_abs_2401_15106
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Underspecified Human Decision Experiments Considered Harmful
Hullman, Jessica
Kale, Alex
Hartline, Jason
Human-Computer Interaction
Artificial Intelligence
Decision-making with information displays is a key focus of research in areas like human-AI collaboration and data visualization. However, what constitutes a decision problem, and what is required for an experiment to conclude that decisions are flawed, remain imprecise. We present a widely applicable definition of a decision problem synthesized from statistical decision theory and information economics. We claim that to attribute loss in human performance to bias, an experiment must provide the information that a rational agent would need to identify the normative decision. We evaluate whether recent empirical research on AI-assisted decisions achieves this standard. We find that only 10 (26%) of 39 studies that claim to identify biased behavior presented participants with sufficient information to make this claim in at least one treatment condition. We motivate the value of studying well-defined decision problems by describing a characterization of performance losses they allow to be conceived.
title Underspecified Human Decision Experiments Considered Harmful
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2401.15106