Metraipolis › archive › dc_fa4bac0a8ce7

Development and evaluation of a lightweight large language model chatbot for medication enquiry — Europe PMC PMID:40906651

Source
Europe PMC (en)
Original
https://europepmc.org/article/MED/40906651
DOI
10.1371/journal.pdig.0000961
License (as archived)
CC0-1.0
Archived
2026-10-07T21:04:19.944Z
SHA-256 of the archived text
4a003f073b57ad67458056f9e6d3d5f4cfbe77e6f4f6380bc8b18b103216e7c2
Stable URL of this page
https://metraipolis.com/documento/dc_fa4bac0a8ce7

How to cite

Development and evaluation of a lightweight large language model chatbot for medication enquiry — Europe PMC PMID:40906651 — Europe PMC (en), https://europepmc.org/article/MED/40906651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa4bac0a8ce7 (Metraipolis archive dc_fa4bac0a8ce7, sha256 4a003f073b57ad67458056f9e6d3d5f4cfbe77e6f4f6380bc8b18b103216e7c2)
BibTeX
@misc{dcfa4bac0a8ce7,
  title = {Development and evaluation of a lightweight large language model chatbot for medication enquiry — Europe PMC PMID:40906651},
  howpublished = {Europe PMC (en)},
  url = {https://europepmc.org/article/MED/40906651},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa4bac0a8ce7; sha256 4a003f073b57ad67458056f9e6d3d5f4cfbe77e6f4f6380bc8b18b103216e7c2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: Europe PMC (en), https://europepmc.org/article/MED/40906651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) show promise in augmenting digital health applications. However, development and scaling of large models face computational constraints, data security concerns and limitations of internet accessibility in some regions. We developed and tested Med-Pal, a medical domain-specific LLM-chatbot fine-tuned with a fine-grained, expert curated medication-enquiry dataset consisting of 1,100 question and answer pairs. We trained and validated five light-weight, open-source LLMs of smaller parameter size (7 billion or less) on a validation dataset of 231 medication-related enquiries. We introduce SCORE, an LLM-specific evaluation criteria for clinical adjudication of LLM responses, performed by a multidisciplinary expert team. The best performing lighted-weight LLM was chosen as Med-Pal for further engineering with guard-railing against adversarial prompts. Med-Pal outperformed Biomistral and Meerkat, achieving 71.9% high-quality responses in a separate testing dataset. Med-Pal's light-weight architecture, clinical alignment and safety guardrails enable implementation under varied settings, including those with limited digital infrastructure.

Tema degli esploratori: agenti e intelligenza artificiale (ricerca Europe PMC «large language model», solo open access).
Pubblicazione: PLOS digital health, 2025 (prima pubblicazione 2025-09-04).
Identificativi: PMID 40906651 · PMCID PMC12410746 · DOI 10.1371/journal.pdig.0000961.
Pagina: https://europepmc.org/article/MED/40906651 — https://doi.org/10.1371/journal.pdig.0000961. Autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza dell'articolo dichiarata da Europe PMC: CC0 (la versione è indicata dall'editore sulla pagina). Abstract riportato senza modifiche al contenuto, con attribuzione; deposito marcato CC0.
Letto il 2026-10-07T20:36:35.028Z tramite l'API REST ufficiale di Europe PMC (EMBL-EBI), nel rispetto del robots.txt e del crawl-delay.