Unexploited Information Value in Human-AI Collaboration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Ziyang, Wu, Yifan, Hartline, Jason, Hullman, Jessica
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912244155023360
author Guo, Ziyang
Wu, Yifan
Hartline, Jason
Hullman, Jessica
author_facet Guo, Ziyang
Wu, Yifan
Hartline, Jason
Hullman, Jessica
contents Humans and AIs are often paired on decision tasks with the expectation of achieving complementary performance -- where the combination of human and AI outperforms either one alone. However, how to improve performance of a human-AI team is often not clear without knowing more about what particular information and strategies each agent employs. In this paper, we propose a model based in statistical decision theory to analyze human-AI collaboration from the perspective of what information could be used to improve a human or AI decision. We demonstrate our model on a deepfake detection task to investigate seven video-level features by their unexploited value of information. We compare the human alone, AI alone and human-AI team and offer insights on how the AI assistance impacts people's usage of the information and what information that the AI exploits well might be useful for improving human decisions.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10463
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unexploited Information Value in Human-AI Collaboration
Guo, Ziyang
Wu, Yifan
Hartline, Jason
Hullman, Jessica
Human-Computer Interaction
Artificial Intelligence
Humans and AIs are often paired on decision tasks with the expectation of achieving complementary performance -- where the combination of human and AI outperforms either one alone. However, how to improve performance of a human-AI team is often not clear without knowing more about what particular information and strategies each agent employs. In this paper, we propose a model based in statistical decision theory to analyze human-AI collaboration from the perspective of what information could be used to improve a human or AI decision. We demonstrate our model on a deepfake detection task to investigate seven video-level features by their unexploited value of information. We compare the human alone, AI alone and human-AI team and offer insights on how the AI assistance impacts people's usage of the information and what information that the AI exploits well might be useful for improving human decisions.
title Unexploited Information Value in Human-AI Collaboration
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2411.10463