Preprint · 2025 · Open access

Large Language Models are overconfident and amplify human bias

Sun, Fengfei, Ningke Li, Kailong Wang, Lorenz F. Goette

arXiv (Cornell University) · Published 4 May 2025 · DOI 10.48550/arxiv.2505.02151

Open PDFView at the publisherCite this paper

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

All highly cited Computer Science papers

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.