Journal article · 2026 · Open access

Agentic Hallucination Risk Scoring for Medical LLMs via Uncertainty Quantification and Clinical Knowledge Injection

Mayank Kapadia, Mohammad Masum

Algorithms, 19(4), 315 · Published 17 April 2026 · DOI 10.3390/a19040315

Open PDFView at the publisherCite this paper

In brief

“Agentic Hallucination Risk Scoring for Medical LLMs via Uncertainty Quantification and Clinical Knowledge Injection” is a 2026 journal article by Mayank Kapadia and Mohammad Masum, published in Algorithms. 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 Algorithms.

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.01
References
28
Authors
2

Abstract

Large Language Models (LLMs) have witnessed significant adoption across numerous domains since 2020, but their proclivity to hallucinate creates unacceptable dangers in high-risk environments like healthcare, where wrong outputs can directly jeopardize human safety. While present systems focus on pre-generation mitigation strategies, they cannot ensure the safety of individual outputs during inference. We provide a post hoc Hallucination Risk Scoring (HRS) methodology that intercepts questionable outputs before they reach patients via an agentic pipeline. Given a medical question, a domain-specific LLM generates an initial response from which five complimentary uncertainty signals are computed, which are then separated into a decision layer that governs escalation and a guidance layer that directs clinical knowledge injection by a GPT. The framework is tested using three biological question-answering datasets of various complexity: PubMedQA-Labeled, PubMedQA-Artificial, and BioASQ Task B. The results show an up to 38% safety increase at the most sensitive threshold configuration, zero deterioration across all experimental configurations enforced by the Revert Baseline method, and complexity-aware escalation rates that scale organically with dataset difficulty. Tunable thresholds allow physicians to calibrate system behavior based on deployment requirements, providing a practical safety–accuracy trade-off. Statistical research finds entropy as the primary uncertainty signal separating escalated from non-escalated situations across all datasets. These findings provide a deployable, interpretable, and configurable post hoc safety paradigm for reliable medical AI implementation.

Cite this paper

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

APA 7

Kapadia, M., & Masum, M. (2026). Agentic Hallucination Risk Scoring for Medical LLMs via Uncertainty Quantification and Clinical Knowledge Injection. Algorithms, 19(4), 315. https://doi.org/10.3390/a19040315

MLA 9

Kapadia, Mayank, and Mohammad Masum. “Agentic Hallucination Risk Scoring for Medical LLMs via Uncertainty Quantification and Clinical Knowledge Injection.” Algorithms, vol. 19, no. 4, 2026, p. 315. https://doi.org/10.3390/a19040315.

Chicago

Kapadia, Mayank and Mohammad Masum. 2026. “Agentic Hallucination Risk Scoring for Medical LLMs via Uncertainty Quantification and Clinical Knowledge Injection.” Algorithms 19 (4): 315. https://doi.org/10.3390/a19040315.

Harvard

Kapadia, M. and Masum, M. (2026) ‘Agentic Hallucination Risk Scoring for Medical LLMs via Uncertainty Quantification and Clinical Knowledge Injection’, Algorithms, 19(4), p. 315. doi:10.3390/a19040315.

IEEE

M. Kapadia and M. Masum, “Agentic Hallucination Risk Scoring for Medical LLMs via Uncertainty Quantification and Clinical Knowledge Injection,” Algorithms, vol. 19, no. 4, p. 315, 2026, doi: 10.3390/a19040315.

BibTeX

@article{kapadia2026agentic,
  title     = {{Agentic Hallucination Risk Scoring for Medical LLMs via Uncertainty Quantification and Clinical Knowledge Injection}},
  author    = {Kapadia, Mayank and Masum, Mohammad},
  journal   = {Algorithms},
  year      = {2026},
  volume    = {19},
  number    = {4},
  pages     = {315},
  doi       = {10.3390/a19040315},
  url       = {https://doi.org/10.3390/a19040315}
}

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
  • uncertainty quantification
  • medical question answering
  • PubMedQA

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?

Kapadia, M., & Masum, M. (2026). Agentic Hallucination Risk Scoring for Medical LLMs via Uncertainty Quantification and Clinical Knowledge Injection. Algorithms, 19(4), 315. https://doi.org/10.3390/a19040315

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 Algorithms: sign in and open the PDF from this page.

Who wrote this paper?

Mayank Kapadia, Mohammad Masum.

What is the DOI of this paper?

10.3390/a19040315, permanently at https://doi.org/10.3390/a19040315. 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.