A Benchmark for Long-Form Medical Question Answering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hosseini, Pedram, Sin, Jessica M., Ren, Bing, Thomas, Bryceton G., Nouri, Elnaz, Farahanchi, Ali, Hassanpour, Saeed
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909396177518592
author Hosseini, Pedram
Sin, Jessica M.
Ren, Bing
Thomas, Bryceton G.
Nouri, Elnaz
Farahanchi, Ali
Hassanpour, Saeed
author_facet Hosseini, Pedram
Sin, Jessica M.
Ren, Bing
Thomas, Bryceton G.
Nouri, Elnaz
Farahanchi, Ali
Hassanpour, Saeed
contents There is a lack of benchmarks for evaluating large language models (LLMs) in long-form medical question answering (QA). Most existing medical QA evaluation benchmarks focus on automatic metrics and multiple-choice questions. While valuable, these benchmarks fail to fully capture or assess the complexities of real-world clinical applications where LLMs are being deployed. Furthermore, existing studies on evaluating long-form answer generation in medical QA are primarily closed-source, lacking access to human medical expert annotations, which makes it difficult to reproduce results and enhance existing baselines. In this work, we introduce a new publicly available benchmark featuring real-world consumer medical questions with long-form answer evaluations annotated by medical doctors. We performed pairwise comparisons of responses from various open and closed-source medical and general-purpose LLMs based on criteria such as correctness, helpfulness, harmfulness, and bias. Additionally, we performed a comprehensive LLM-as-a-judge analysis to study the alignment between human judgments and LLMs. Our preliminary results highlight the strong potential of open LLMs in medical QA compared to leading closed models. Code & Data: https://github.com/lavita-ai/medical-eval-sphere
format Preprint
id arxiv_https___arxiv_org_abs_2411_09834
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Benchmark for Long-Form Medical Question Answering
Hosseini, Pedram
Sin, Jessica M.
Ren, Bing
Thomas, Bryceton G.
Nouri, Elnaz
Farahanchi, Ali
Hassanpour, Saeed
Computation and Language
Artificial Intelligence
There is a lack of benchmarks for evaluating large language models (LLMs) in long-form medical question answering (QA). Most existing medical QA evaluation benchmarks focus on automatic metrics and multiple-choice questions. While valuable, these benchmarks fail to fully capture or assess the complexities of real-world clinical applications where LLMs are being deployed. Furthermore, existing studies on evaluating long-form answer generation in medical QA are primarily closed-source, lacking access to human medical expert annotations, which makes it difficult to reproduce results and enhance existing baselines. In this work, we introduce a new publicly available benchmark featuring real-world consumer medical questions with long-form answer evaluations annotated by medical doctors. We performed pairwise comparisons of responses from various open and closed-source medical and general-purpose LLMs based on criteria such as correctness, helpfulness, harmfulness, and bias. Additionally, we performed a comprehensive LLM-as-a-judge analysis to study the alignment between human judgments and LLMs. Our preliminary results highlight the strong potential of open LLMs in medical QA compared to leading closed models. Code & Data: https://github.com/lavita-ai/medical-eval-sphere
title A Benchmark for Long-Form Medical Question Answering
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2411.09834