EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Combining Anti-Hallucination Strategies for Reliable LLM-Based Clinical Information Extraction

Jean Yapo, Chuanming Dong, Marc Cuggia, Boris Delange

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260351 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Jean Yapo und 3 weiteren Autor:innen. Beteiligte Einrichtung: Univ Rennes, CHU Rennes, INSERM, LTSI-UMR 1099, Rennes, France. Hauptthemen laut MEDLINE: Large Language Models, Hallucinations, Natural Language Processing, Electronic Health Records. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a novel LLM-based approach for medical concept extraction that combines multiple anti-hallucination strategies. Our Streamlit web application enables flexible pipeline configuration through ensemble methods, Chain-of-Verification, contextual grounding, and LLM-as-a-Judge mechanisms. This modular framework addresses the critical challenge of hallucinations in clinical text processing, particularly for smaller models required in privacy-constrained hospital environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsHallucinationsNatural Language ProcessingElectronic Health RecordsData MiningInformation Storage and RetrievalHumans

Stichwörter der Autor:innen

HallucinationLarge Language ModelMedical Data Extraction

Autor:innen und Institutionen

  • Univ Rennes, CHU Rennes, INSERM, LTSI-UMR 1099, Rennes, France.
  • IMT Atlantique, Brest, France.

Zitieren

APA

Yapo, J., Dong, C., Cuggia, M., & Delange, B. (2026). Combining Anti-Hallucination Strategies for Reliable LLM-Based Clinical Information Extraction. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260351

Vancouver

Yapo J, Dong C, Cuggia M, Delange B. Combining Anti-Hallucination Strategies for Reliable LLM-Based Clinical Information Extraction. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260351

BibTeX
@article{Yapo2026,
  author = {Yapo, Jean and Dong, Chuanming and Cuggia, Marc and Delange, Boris},
  title = {Combining Anti-Hallucination Strategies for Reliable LLM-Based Clinical Information Extraction},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260351}
}
Kostenlos starten →