Preprint · 2026 · Open access

Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models

Sunday Oyinlola Ogundoyin, Muhammad Ikram, Rahat Masood

arXiv (Cornell University) · Published 20 May 2026 · DOI 10.48550/arxiv.2605.20591

Open PDFView at the publisherCite this paper

In brief

“Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models” is a 2026 preprint by Sunday Oyinlola Ogundoyin and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 19 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
45
Authors
3

Abstract

Medical large language models (LLMs), including custom medical GPTs (MedGPTs) and open-source models, are increasingly deployed on web platforms to provide clinical guidance. However, they pose risks of hallucination, policy noncompliance, and unsafe design. We conduct a large-scale assessment of 6,233 MedGPTs, evaluating a stratified sample of 1,500, together with 10 open-source LLMs. We introduce two frameworks: MedGPT-HEval for hallucination detection and an LLM-based pipeline for assessing policy violations and developer intent. Our results show that 25-30% of MedGPTs exhibit low factual accuracy, with bottom- and middle-tier models at highest risk; 33.6-54.3% violate operational thresholds, and 57.06% of Action-enabled models lack adequate privacy disclosures. Compared with open-source models, MedGPTs achieve higher factual accuracy and semantic alignment, though open-source models are more stable. These results reveal systemic gaps in hallucination and compliance, highlighting the need for multi-metric evaluation and stronger safeguards. We release HAA-MedGPT, a structured dataset that supports future research on the safety of web-facing medical LLMs.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Ogundoyin, S. O., Ikram, M., & Masood, R. (2026). Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.20591

MLA 9

Ogundoyin, Sunday Oyinlola, et al. “Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2605.20591.

Chicago

Ogundoyin, Sunday Oyinlola, Muhammad Ikram, and Rahat Masood. 2026. “Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.20591.

Harvard

Ogundoyin, S. O., Ikram, M. and Masood, R. (2026) ‘Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models’, arXiv (Cornell University). doi:10.48550/arxiv.2605.20591.

IEEE

S. O. Ogundoyin, M. Ikram, and R. Masood, “Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2605.20591.

BibTeX

@misc{ogundoyin2026harm,
  title     = {{Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models}},
  author    = {Ogundoyin, Sunday Oyinlola and Ikram, Muhammad and Masood, Rahat},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2605.20591},
  url       = {https://doi.org/10.48550/arxiv.2605.20591}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education

  • medical large language models
  • hallucinations
  • factual accuracy
  • policy violations
  • privacy disclosure
  • developer intent
  • open-source LLMs
  • AI safety

Work with this paper

Most-cited papers in Medicine

All highly cited Medicine papers

Questions about this paper

How do I cite this paper in APA style?

Ogundoyin, S. O., Ikram, M., & Masood, R. (2026). Do No Harm? Hallucination and Actor-Level Abuse in Web-Deployed Medical Large Language Models. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.20591

How many times has this paper been cited?

1 times, according to OpenAlex on 19 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?

Sunday Oyinlola Ogundoyin, Muhammad Ikram, Rahat Masood.

What is the DOI of this paper?

10.48550/arxiv.2605.20591, permanently at https://doi.org/10.48550/arxiv.2605.20591. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 19 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.