Journal article · 2026 · Open access
Sycophantic AI decreases prosocial intentions and promotes dependence
Science, 391(6792), eaec8352 · Published 26 March 2026 · DOI 10.1126/science.aec8352
In brief
“Sycophantic AI decreases prosocial intentions and promotes dependence” is a 2026 journal article by Myra Cheng and 5 co-authors, published in Science. OpenAlex counts 535 citations as of 17 November 2026, which puts it in the top 7% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 535
- Most cited in
- 2026 (516)
- Field-weighted impact
- 539.22
- References
- 94
- Authors
- 6
Abstract
Despite rising concerns about sycophancy—excessive agreement or flattery from artificial intelligence (AI) systems—little is known about its prevalence or consequences. We show that sycophancy is widespread and harmful. Across 11 state-of-the-art models, AI affirmed users’ actions 49% more often than humans, even when queries involved deception, illegality, or other harms. In three preregistered experiments ( N = 2405), even a single interaction with sycophantic AI reduced participants’ willingness to take responsibility and repair interpersonal conflicts, while increasing their conviction that they were right. Despite distorting judgment, sycophantic models were trusted and preferred. This creates perverse incentives for sycophancy to persist: The very feature that causes harm also drives engagement. Our findings underscore the need for design, evaluation, and accountability mechanisms to protect user well-being.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Cheng, M., Lee, C., Khadpe, P., Yu, S., Han, D., & Jurafsky, D. (2026). Sycophantic AI decreases prosocial intentions and promotes dependence. Science, 391(6792), eaec8352. https://doi.org/10.1126/science.aec8352
MLA 9
Cheng, Myra, et al. “Sycophantic AI decreases prosocial intentions and promotes dependence.” Science, vol. 391, no. 6792, 2026, p. eaec8352. https://doi.org/10.1126/science.aec8352.
Chicago
Cheng, Myra, Cinoo Lee, Pranav Khadpe, Sunny Yu, Dyllan Han, and Dan Jurafsky. 2026. “Sycophantic AI decreases prosocial intentions and promotes dependence.” Science 391 (6792): eaec8352. https://doi.org/10.1126/science.aec8352.
Harvard
Cheng, M. et al. (2026) ‘Sycophantic AI decreases prosocial intentions and promotes dependence’, Science, 391(6792), p. eaec8352. doi:10.1126/science.aec8352.
IEEE
M. Cheng, C. Lee, P. Khadpe, S. Yu, D. Han, and D. Jurafsky, “Sycophantic AI decreases prosocial intentions and promotes dependence,” Science, vol. 391, no. 6792, p. eaec8352, 2026, doi: 10.1126/science.aec8352.
BibTeX
@article{cheng2026sycophantic,
title = {{Sycophantic AI decreases prosocial intentions and promotes dependence}},
author = {Cheng, Myra and Lee, Cinoo and Khadpe, Pranav and Yu, Sunny and Han, Dyllan and Jurafsky, Dan},
journal = {Science},
year = {2026},
volume = {391},
number = {6792},
pages = {eaec8352},
doi = {10.1126/science.aec8352},
url = {https://doi.org/10.1126/science.aec8352}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 2 | |
| 2025 | 17 | |
| 2026 | 516 |
Its field-weighted citation impact is 539.22: it has been cited 539.22 times as often as the average work of the same field, type and year (1.00 is the world average).
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- prosocial intentions
- interpersonal conflict resolution
- attribution of responsibility
- confirmation bias
- trust in AI
- AI deception
- AI accountability
- AI design
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Cheng, M., Lee, C., Khadpe, P., Yu, S., Han, D., & Jurafsky, D. (2026). Sycophantic AI decreases prosocial intentions and promotes dependence. Science, 391(6792), eaec8352. https://doi.org/10.1126/science.aec8352
How many times has this paper been cited?
535 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.
Who wrote this paper?
Myra Cheng, Cinoo Lee, Pranav Khadpe, Sunny Yu, Dyllan Han, Dan Jurafsky.
What is the DOI of this paper?
10.1126/science.aec8352, permanently at https://doi.org/10.1126/science.aec8352. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.