Pareto-Optimized Open-Source LLMs for Healthcare via Context Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bayarri-Planas, Jordi, Gururajan, Ashwin Kumar, Garcia-Gasulla, Dario
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913773865926656
author Bayarri-Planas, Jordi
Gururajan, Ashwin Kumar
Garcia-Gasulla, Dario
author_facet Bayarri-Planas, Jordi
Gururajan, Ashwin Kumar
Garcia-Gasulla, Dario
contents This study leverages optimized context retrieval to enhance open-source Large Language Models (LLMs) for cost-effective, high performance healthcare AI. We demonstrate that this approach achieves state-of-the-art accuracy on medical question answering at a fraction of the cost of proprietary models, significantly improving the cost-accuracy Pareto frontier on the MedQA benchmark. Key contributions include: (1) OpenMedQA, a novel benchmark revealing a performance gap in open-ended medical QA compared to multiple-choice formats; (2) a practical, reproducible pipeline for context retrieval optimization; and (3) open-source resources (Prompt Engine, CoT/ToT/Thinking databases) to empower healthcare AI development. By advancing retrieval techniques and QA evaluation, we enable more affordable and reliable LLM solutions for healthcare.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15127
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Pareto-Optimized Open-Source LLMs for Healthcare via Context Retrieval
Bayarri-Planas, Jordi
Gururajan, Ashwin Kumar
Garcia-Gasulla, Dario
Artificial Intelligence
I.2.0; I.2.7
This study leverages optimized context retrieval to enhance open-source Large Language Models (LLMs) for cost-effective, high performance healthcare AI. We demonstrate that this approach achieves state-of-the-art accuracy on medical question answering at a fraction of the cost of proprietary models, significantly improving the cost-accuracy Pareto frontier on the MedQA benchmark. Key contributions include: (1) OpenMedQA, a novel benchmark revealing a performance gap in open-ended medical QA compared to multiple-choice formats; (2) a practical, reproducible pipeline for context retrieval optimization; and (3) open-source resources (Prompt Engine, CoT/ToT/Thinking databases) to empower healthcare AI development. By advancing retrieval techniques and QA evaluation, we enable more affordable and reliable LLM solutions for healthcare.
title Pareto-Optimized Open-Source LLMs for Healthcare via Context Retrieval
topic Artificial Intelligence
I.2.0; I.2.7
url https://arxiv.org/abs/2409.15127