Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Comment
. 2023 Mar 21;27(1):120.
doi: 10.1186/s13054-023-04393-x.

Large language models and the perils of their hallucinations

Razvan Azamfirei  1 , Sapna R Kudchadkar  2   3 , James Fackler  2   3
Affiliations
Comment

Large language models and the perils of their hallucinations

Razvan Azamfirei et al. Crit Care. .
No abstract available

PubMed Disclaimer

Conflict of interest statement

JF is a Board Member of Machine Learning for Healthcare and a founder of Rubicon Health LLC. The remaining authors do not have any potential competing interests.

Comment in

Comment on

References

    1. Salvagno M, Taccone FS, Gerli AG. Can artificial intelligence help for scientific writing? Crit Care. 2023;27(1):75. doi: 10.1186/s13054-023-04380-2. - DOI - PMC - PubMed
    1. OpenAI. ChatGPT General FAQ. 2023. https://web.archive.org/web/20230226171118/https://help.openai.com/en/ar.... Accessed on 26 Feb 2023.
    1. Belohlavek J, Smalcova J, Rob D, Franek O, Smid O, Pokorna M, et al. Effect of intra-arrest transport, extracorporeal cardiopulmonary resuscitation, and immediate invasive assessment and treatment on functional neurologic outcome in refractory out-of-hospital cardiac arrest: a randomized clinical trial. JAMA. 2022;327(8):737–747. doi: 10.1001/jama.2022.1025. - DOI - PMC - PubMed
    1. OpenAI. ChatGPT: Optimizing Language Models for Dialogue. 2022. https://web.archive.org/web/20230225211409/https://openai.com/blog/chatgpt/. Accessed on 26 Feb 2023.
    1. Zamfirescu-Pereira J, Wong R, Hartmann B, Yang Q, editors. Why Johnny can’t prompt: how non-AI experts try (and fail) to design LLM prompts. In: Proceedings of the 2023 CHI conference on human factors in computing systems (CHI ’23); 2023; Hamburg, Germany. 10.1145/3544548.3581388. https://www.researchgate.net/publication/368577310_Why_Johnny_Can't_Prom.... Accessed on 02/26/2023.

LinkOut - more resources