Generative AI Are More Truth-Biased Than Humans: A Replication and Extension of Core Truth-Default Theory Principles-Reference-Cited by-同舟云学术

Generative AI Are More Truth-Biased Than Humans: A Replication and Extension of Core Truth-Default Theory Principles

Published:2023-12-19 Issue:2 Volume:43 Page:261-267
ISSN:0261-927X
Container-title:Journal of Language and Social Psychology
language:en
Short-container-title:Journal of Language and Social Psychology

Author:

Markowitz David M.¹^ORCID,Hancock Jeffrey T.²

Affiliation:

1. Department of Communication, Michigan State University, East Lansing, MI, USA

2. Department of Communication, Stanford University, Stanford, CA, USA

Abstract

Humans often display a truth-bias—the perception that others are honest independent of message veracity—but does this phenomenon extend to generative artificial intelligence (AI)? We had humans and large language models make nearly 1,000 veracity judgments across different prompts. Human detection accuracies were near chance (50%–53%) with notable truth-biases (59%–64%); AI had a substantially greater truth-bias than humans (67%–99%). GPT-4 was also truth-default, not suspecting deception when veracity assessments were unprompted. Together, people and AI judge most information to be true.

Publisher

SAGE Publications

Subject

Linguistics and Language,Sociology and Political Science,Anthropology,Language and Linguistics,Education,Social Psychology

Link

http://journals.sagepub.com/doi/pdf/10.1177/0261927X231220404

Reference14 articles.

1. Documenting the Truth-Default: The Low Frequency of Spontaneous Unprompted Veracity Assessments in Deception Detection

2. Cues to deception.

3. How mental systems believe.

4. Why do lie-catchers fail? A lens model meta-analysis of human lie judgments.

5. Truth-Default Theory (TDT)

Cited by 6 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. The good, the bad, and the GPT: Reviewing the impact of generative artificial intelligence on psychology;Current Opinion in Psychology;2024-10

2. Self and other-perceived deception detection abilities are highly correlated but unassociated with objective detection ability: Examining the detection consensus effect;Scientific Reports;2024-07-30

3. Generative AI in Technical Communication: A Review of Research from 2023 to 2024;Journal of Technical Writing and Communication;2024-06-11

4. Self and Other-Perceived Deception Detection Abilities are Highly Correlated but Unassociated with Objective Detection Ability: Examining the Detection Consensus Effect;2024-06-11

5. Lie–truth judgments: adaptive lie detector account and truth-default theory compared and contrasted;Communication Theory;2024-05-31