Saved in:
Bibliographic Details
Main Authors: Bolton, William James, Poyiadzi, Rafael, Morrell, Edward R., Bueno, Gabriela van Bergen Gonzalez, Goetz, Lea
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.14578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913276912205824
author Bolton, William James
Poyiadzi, Rafael
Morrell, Edward R.
Bueno, Gabriela van Bergen Gonzalez
Goetz, Lea
author_facet Bolton, William James
Poyiadzi, Rafael
Morrell, Edward R.
Bueno, Gabriela van Bergen Gonzalez
Goetz, Lea
contents Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. In this work we introduce the Reliability AssesMent for Biomedical LLM Assistants (RAmBLA) framework and evaluate whether four state-of-the-art foundation LLMs can serve as reliable assistants in the biomedical domain. We identify prompt robustness, high recall, and a lack of hallucinations as necessary criteria for this use case. We design shortform tasks and tasks requiring LLM freeform responses mimicking real-world user interactions. We evaluate LLM performance using semantic similarity with a ground truth response, through an evaluator LLM.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14578
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain
Bolton, William James
Poyiadzi, Rafael
Morrell, Edward R.
Bueno, Gabriela van Bergen Gonzalez
Goetz, Lea
Machine Learning
Artificial Intelligence
Large Language Models (LLMs) increasingly support applications in a wide range of domains, some with potential high societal impact such as biomedicine, yet their reliability in realistic use cases is under-researched. In this work we introduce the Reliability AssesMent for Biomedical LLM Assistants (RAmBLA) framework and evaluate whether four state-of-the-art foundation LLMs can serve as reliable assistants in the biomedical domain. We identify prompt robustness, high recall, and a lack of hallucinations as necessary criteria for this use case. We design shortform tasks and tasks requiring LLM freeform responses mimicking real-world user interactions. We evaluate LLM performance using semantic similarity with a ground truth response, through an evaluator LLM.
title RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2403.14578