Gemini Update Clinical decision support based on Bevacizumab cancer trials and pushing the limitations of advanced LLMs

Fuente: Zenodo
Salvato in:
Dettagli Bibliografici
Autore principale: Kawchak, Kevin
Natura: Recurso digital
Lingua:inglese
Pubblicazione: Zenodo 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866901709083639808
author Kawchak, Kevin
author_facet Kawchak, Kevin
contents <p>BREAKING: Exact Recall Milestone for Challenging Clinical Decision Support Task This update to the full January 27, 2025 study significantly improves on Standard 2a results regarding a reasoning Large Language Model’s ability to provide exact recall of author citations and quotations on a comprehensive input [1]. 100 Bevacizumab cancer therapy articles representing over 900K words were previously summarized into 100 reports totaling 49K words, and have now been analyzed by Google Gemini to yield a more accurate clinical decision support (CDS) study. The primarily limitation of the model was less advanced reasoning ability versus current OpenAI o1 and o3-mini models. The relevance of highly accurate quotations and citations is that clinical researchers require consistent and verifiable information along with LLM contextual awareness of clinical studies with associated speed advantages.</p>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_14968289
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle Gemini Update Clinical decision support based on Bevacizumab cancer trials and pushing the limitations of advanced LLMs
Kawchak, Kevin
Gemini
Claude
LLM
Clinical decision support
Bevacizumab cancer trials
AI
<p>BREAKING: Exact Recall Milestone for Challenging Clinical Decision Support Task This update to the full January 27, 2025 study significantly improves on Standard 2a results regarding a reasoning Large Language Model’s ability to provide exact recall of author citations and quotations on a comprehensive input [1]. 100 Bevacizumab cancer therapy articles representing over 900K words were previously summarized into 100 reports totaling 49K words, and have now been analyzed by Google Gemini to yield a more accurate clinical decision support (CDS) study. The primarily limitation of the model was less advanced reasoning ability versus current OpenAI o1 and o3-mini models. The relevance of highly accurate quotations and citations is that clinical researchers require consistent and verifiable information along with LLM contextual awareness of clinical studies with associated speed advantages.</p>
title Gemini Update Clinical decision support based on Bevacizumab cancer trials and pushing the limitations of advanced LLMs
topic Gemini
Claude
LLM
Clinical decision support
Bevacizumab cancer trials
AI
url https://doi.org/10.5281/zenodo.14968289