Paper · 2026 · Open access

Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning

Yiming Liao, Zeno Franco, Jose Lizarraga Mazaba, Keke Chen

Digital Repository at the University of Maryland (University of Maryland College Park) · Published 31 May 2026 · DOI 10.13016/m2fank-jqac

Open full textCite this paper

In brief

“Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning” is a 2026 paper by Yiming Liao and 3 co-authors, published in Digital Repository at the University of Maryland (University of Maryland College Park). OpenAlex counts 1 citations as of 19 November 2026. It is open access: the full text is free to read at Digital Repository at the University of Maryland (University of Maryland College Park).

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.03
Authors
4

Abstract

Hallucinations in medical large language models (LLMs) pose serious risks for clinical decision support, particularly when models must reason over complex electronic health records (EHRs). However, existing benchmarks often lack a realistic clinical context and provide limited insight into how hallucinations can be mitigated in practice. We introduce Med-HEAL, a framework for systematically identifying, analyzing, and mitigating hallucinations in medical LLMs using clinically grounded data. Building on the EHRNoteQA benchmark derived from MIMIC-IV discharge summaries, we construct a hallucination dataset by evaluating BioMistral-7B on open-ended clinical question answering tasks. Model outputs are labeled through a dual evaluation pipeline that combines LLM-as-a-Judge assessment (GPT-4o) with human auditing by medical student reviewers, producing correctness judgments and annotations of reasoning errors via a custom web-based evaluation system. We then leverage this dataset to investigate mitigation strategies: a self-critique pipeline, in which the test model reviews its own answers to detect potential errors and regenerates responses for flagged cases, and retrieval-augmented in-context learning (RA-ICL), which exposes the model to hallucinated and corrected examples. Experiments across five open-source LLMs-BioMistral, Llama-3.1, DeepSeek, Qwen2.5, and Qwen3, show that the self-critique strategy improves accuracy for three of five models (p < 0.05) without requiring parameter updates. Med-HEAL provides both a reusable hallucination dataset and a practical framework for studying and mitigating hallucinations in medical LLMs, supporting safer deployment of AI systems in clinical environments. Our code and data are publicly available at https://github.com/yimingliao-blad/med-heal.git.

Cite this paper

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

APA 7

Liao, Y., Franco, Z., Mazaba, J. L., & Chen, K. (2026). Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning. Digital Repository at the University of Maryland (University of Maryland College Park). https://doi.org/10.13016/m2fank-jqac

MLA 9

Liao, Yiming, et al. “Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning.” Digital Repository at the University of Maryland (University of Maryland College Park), 2026. https://doi.org/10.13016/m2fank-jqac.

Chicago

Liao, Yiming, Zeno Franco, Jose Lizarraga Mazaba, and Keke Chen. 2026. “Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning.” Digital Repository at the University of Maryland (University of Maryland College Park). https://doi.org/10.13016/m2fank-jqac.

Harvard

Liao, Y. et al. (2026) ‘Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning’, Digital Repository at the University of Maryland (University of Maryland College Park). doi:10.13016/m2fank-jqac.

IEEE

Y. Liao, Z. Franco, J. L. Mazaba, and K. Chen, “Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning,” Digital Repository at the University of Maryland (University of Maryland College Park), 2026, doi: 10.13016/m2fank-jqac.

BibTeX

@article{liao2026heal,
  title     = {{Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning}},
  author    = {Liao, Yiming and Franco, Zeno and Mazaba, Jose Lizarraga and Chen, Keke},
  journal   = {Digital Repository at the University of Maryland (University of Maryland College Park)},
  year      = {2026},
  doi       = {10.13016/m2fank-jqac},
  url       = {https://doi.org/10.13016/m2fank-jqac}
}

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

  • hallucination mitigation
  • medical large language models
  • in-context learning
  • self-criticism
  • medical question answering
  • electronic health records
  • LLM-as-a-judge
  • clinical decision support

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?

Liao, Y., Franco, Z., Mazaba, J. L., & Chen, K. (2026). Med-HEAL: Analyzing and Mitigating Hallucinations in Medical LLMs with Hallucination-Aware In-Context Learning. Digital Repository at the University of Maryland (University of Maryland College Park). https://doi.org/10.13016/m2fank-jqac

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 Digital Repository at the University of Maryland (University of Maryland College Park): sign in and open the full text from this page.

Who wrote this paper?

Yiming Liao, Zeno Franco, Jose Lizarraga Mazaba, Keke Chen.

What is the DOI of this paper?

10.13016/m2fank-jqac, permanently at https://doi.org/10.13016/m2fank-jqac. 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.