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

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.

Keywords

artificial intelligence large language models truth-bias deception detection truth-default theory

Get full access to this article

View all access options for this article.

References

Clare

D. D.

Levine

T. R.

(2019). Documenting the truth-default: The low frequency of spontaneous unprompted veracity assessments in deception detection. Human Communication Research, 45(3), 286–308. https://doi.org/10.1093/hcr/hqz001

DePaulo

B. M.

Malone

B. E.

Lindsay

J. J.

Muhlenbruck

Charlton

Cooper

(2003). Cues to deception. Psychological Bulletin, 129(1), 74–118. https://doi.org/10.1037/0033-2909.129.1.74

Gilbert

D. T.

(1991). How mental systems believe. American Psychologist, 46(2), 107–119. https://doi.org/10.1037/0003-066X.46.2.107

Hartwig

Bond

C. F.

Jr (2011). Why do lie-catchers fail? A lens model meta-analysis of human lie judgments. Psychological Bulletin, 137(4), 643–659. https://doi.org/10.1037/a0023589

Levine

T. R.

(2014). Truth-default theory (TDT): A theory of human deception and deception detection. Journal of Language and Social Psychology, 33(4), 378–392. https://doi.org/10.1177/0261927 ( 14535916

Levine

T. R.

(2020). Duped: Truth-Default Theory and the social science of lying and deception. University of Alabama Press.

Lloyd

E. P.

Deska

J. C.

Hugenberg

McConnell

A. R.

Humphrey

B. T.

Kunstman

J. W.

(2019). Miami University deception detection database. Behavior Research Methods, 51(1), 429–439. https://doi.org/10.3758/s13428-018-1061-4

Luke

T. J.

(2019). Lessons from Pinocchio: Cues to deception may be highly exaggerated. Perspectives on Psychological Science, 14(4), 646–671. https://doi.org/10.1177/1745691619838258

Markowitz

D. M.

Griffin

D. J.

(2020). When context matters: How false, truthful, and genre-related communication styles are revealed in language. Psychology, Crime & Law, 26(3), 287–310. https://doi.org/10.1080/1068316X.2019.1652751

10.

McCornack

S. A.

Parks

M. R.

(1986). Deception detection and relationship development: The other side of trust. Annals of the International Communication Association, 9(1), 377–389. https://doi.org/10.1080/23808985.1986.11678616

11.

Ott

Choi

Cardie

Hancock

J. T.

(2011). Finding deceptive opinion spam by any stretch of the imagination. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 1, 309–319.

12.

Pennebaker

J. W.

Boyd

R. L.

Booth

R. J.

Ashokkumar

Francis

M. E.

(2022). Linguistic inquiry and word count: LIWC-22 [Computer software]. Pennebaker Conglomerates. https://www.liwc.app.

13.

Vrij

(2008). Detecting lies and deceit: Pitfalls and opportunities (2nd ed.). Wiley.

14.

Webb

Holyoak

K. J.

(2023). Emergent analogical reasoning in large language models. Nature Human Behaviour, 7(9), Article 9. https://doi.org/10.1038/s41562-023-01659-w

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.03 MB