Preprint · 2025 · Open access
Large Language Models are overconfident and amplify human bias
arXiv (Cornell University) · Published 4 May 2025 · DOI 10.48550/arxiv.2505.02151
In brief
“Large Language Models are overconfident and amplify human bias” is a 2025 preprint by Sun, Fengfei and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 74 citations as of 20 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).
- Citations
- 74
- Most cited in
- 2026 (49)
- References
- 16
- Authors
- 4
Abstract
Large language models (LLMs) are revolutionizing every aspect of society. They are increasingly used in problem-solving tasks to substitute human assessment and reasoning. LLMs are trained on what humans write and are thus exposed to human bias. We evaluate whether LLMs inherit one of the most widespread human biases: overconfidence. We algorithmically construct reasoning problems with known ground truths. We prompt LLMs to answer these problems and assess the confidence in their answers, closely following similar protocols in human experiments. We find that all five LLMs we study are overconfident: they overestimate the probability that their answer is correct between 20% and 60%. Humans have accuracy similar to the more advanced LLMs, but far lower overconfidence. Although humans and LLMs are similarly biased in questions which they are certain they answered correctly, a key difference emerges between them: LLM bias increases sharply relative to humans if they become less sure that their answers are correct. We also show that LLM input has ambiguous effects on human decision making: LLM input leads to an increase in the accuracy, but it more than doubles the extent of overconfidence in the answers.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Fengfei, S., Li, N., Wang, K., & Goette, L. F. (2025). Large Language Models are overconfident and amplify human bias. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.02151
MLA 9
Fengfei, Sun,, et al. “Large Language Models are overconfident and amplify human bias.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2505.02151.
Chicago
Fengfei, Sun,, Ningke Li, Kailong Wang, and Lorenz F. Goette. 2025. “Large Language Models are overconfident and amplify human bias.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.02151.
Harvard
Fengfei, S. et al. (2025) ‘Large Language Models are overconfident and amplify human bias’, arXiv (Cornell University). doi:10.48550/arxiv.2505.02151.
IEEE
S. Fengfei, N. Li, K. Wang, and L. F. Goette, “Large Language Models are overconfident and amplify human bias,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2505.02151.
BibTeX
@misc{fengfei2025large,
title = {{Large Language Models are overconfident and amplify human bias}},
author = {Fengfei, Sun, and Li, Ningke and Wang, Kailong and Goette, Lorenz F.},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2505.02151},
url = {https://doi.org/10.48550/arxiv.2505.02151}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- large language models
- overconfidence
- calibration
- human bias
- confidence estimation
- automated decision-making
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?
Fengfei, S., Li, N., Wang, K., & Goette, L. F. (2025). Large Language Models are overconfident and amplify human bias. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2505.02151
How many times has this paper been cited?
74 times, according to OpenAlex on 20 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?
Sun, Fengfei, Ningke Li, Kailong Wang, Lorenz F. Goette.
What is the DOI of this paper?
10.48550/arxiv.2505.02151, permanently at https://doi.org/10.48550/arxiv.2505.02151. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 20 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.