Salvato in:
Dettagli Bibliografici
Autori principali: Zhang, Xinyao, Heckmann, Nicole Sonne, Suero, Manuela Del Castillo, Speca, Francesco Paolo, Sessa, Maurizio
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2604.17988
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914491267022848
author Zhang, Xinyao
Heckmann, Nicole Sonne
Suero, Manuela Del Castillo
Speca, Francesco Paolo
Sessa, Maurizio
author_facet Zhang, Xinyao
Heckmann, Nicole Sonne
Suero, Manuela Del Castillo
Speca, Francesco Paolo
Sessa, Maurizio
contents Background: The potential of large language models (LLMs) to automate and support pharmacoepidemiologic study design is an emerging area of interest, yet their reliability remains insufficiently characterized. General-purpose LLMs often display inaccuracies, while the comparative performance of specialized biomedical LLMs in this domain remains unknown. Methods: This study evaluated general-purpose LLMs (GPT-4o and DeepSeek-R1) versus biomedically fine-tuned LLMs (QuantFactory/Bio-Medical-Llama-3-8B-GGUF and Irathernotsay/qwen2-1.5B-medical_qa-Finetune) using 46 protocols (2018-2024) from the HMA-EMA Catalogue and Sentinel System. Performance was assessed across relevance, logic of justification, and ontology-code agreement across multiple coding systems using Least-to-Most (LTM) and Active Prompting strategies. Results: GPT-4o and DeepSeek-R1 paired with LTM prompting achieved the highest relevance and logic of justification scores, with GPT-4o-LTM reaching a median relevance score of 4 in 8 of 9 questions for HMA-EMA protocols. Biomedical LLMs showed lower relevance overall and frequently generated insufficient justification. All LLMs demonstrated limited proficiency in ontology-code mapping, although LTM provided the most consistent improvements in reasoning stability. Conclusion: Off-the-shelf general-purpose LLMs currently offer superior support for pharmacoepidemiologic design compared to biomedical LLMs. Prompt strategy strongly influenced LLM performance.
format Preprint
id arxiv_https___arxiv_org_abs_2604_17988
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Employing General-Purpose and Biomedical Large Language Models with Advanced Prompt Engineering for Pharmacoepidemiologic Study Design
Zhang, Xinyao
Heckmann, Nicole Sonne
Suero, Manuela Del Castillo
Speca, Francesco Paolo
Sessa, Maurizio
Computation and Language
Background: The potential of large language models (LLMs) to automate and support pharmacoepidemiologic study design is an emerging area of interest, yet their reliability remains insufficiently characterized. General-purpose LLMs often display inaccuracies, while the comparative performance of specialized biomedical LLMs in this domain remains unknown. Methods: This study evaluated general-purpose LLMs (GPT-4o and DeepSeek-R1) versus biomedically fine-tuned LLMs (QuantFactory/Bio-Medical-Llama-3-8B-GGUF and Irathernotsay/qwen2-1.5B-medical_qa-Finetune) using 46 protocols (2018-2024) from the HMA-EMA Catalogue and Sentinel System. Performance was assessed across relevance, logic of justification, and ontology-code agreement across multiple coding systems using Least-to-Most (LTM) and Active Prompting strategies. Results: GPT-4o and DeepSeek-R1 paired with LTM prompting achieved the highest relevance and logic of justification scores, with GPT-4o-LTM reaching a median relevance score of 4 in 8 of 9 questions for HMA-EMA protocols. Biomedical LLMs showed lower relevance overall and frequently generated insufficient justification. All LLMs demonstrated limited proficiency in ontology-code mapping, although LTM provided the most consistent improvements in reasoning stability. Conclusion: Off-the-shelf general-purpose LLMs currently offer superior support for pharmacoepidemiologic design compared to biomedical LLMs. Prompt strategy strongly influenced LLM performance.
title Employing General-Purpose and Biomedical Large Language Models with Advanced Prompt Engineering for Pharmacoepidemiologic Study Design
topic Computation and Language
url https://arxiv.org/abs/2604.17988