Saved in:
Bibliographic Details
Main Authors: Cosentino, Cristian, Defilippo, Annamaria, Dossena, Marco, Irwin, Christopher, Joubbi, Sara, Liò, Pietro
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.07308
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913982904795136
author Cosentino, Cristian
Defilippo, Annamaria
Dossena, Marco
Irwin, Christopher
Joubbi, Sara
Liò, Pietro
author_facet Cosentino, Cristian
Defilippo, Annamaria
Dossena, Marco
Irwin, Christopher
Joubbi, Sara
Liò, Pietro
contents HealthBranches is a novel benchmark dataset for medical Question-Answering (Q&A), specifically designed to evaluate complex reasoning in Large Language Models (LLMs). This dataset is generated through a semi-automated pipeline that transforms explicit decision pathways from medical source into realistic patient cases with associated questions and answers. Covering 4,063 case studies across 17 healthcare topics, each data point is based on clinically validated reasoning chains. HealthBranches supports both open-ended and multiple-choice question formats and uniquely includes the full reasoning path for each Q&A. Its structured design enables robust evaluation of LLMs' multi-step inference capabilities, including their performance in structured Retrieval-Augmented Generation (RAG) contexts. HealthBranches establishes a foundation for the development of more trustworthy, interpretable, and clinically reliable LLMs in high-stakes domains while also serving as a valuable resource for educational purposes.
format Preprint
id arxiv_https___arxiv_org_abs_2508_07308
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways
Cosentino, Cristian
Defilippo, Annamaria
Dossena, Marco
Irwin, Christopher
Joubbi, Sara
Liò, Pietro
Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
HealthBranches is a novel benchmark dataset for medical Question-Answering (Q&A), specifically designed to evaluate complex reasoning in Large Language Models (LLMs). This dataset is generated through a semi-automated pipeline that transforms explicit decision pathways from medical source into realistic patient cases with associated questions and answers. Covering 4,063 case studies across 17 healthcare topics, each data point is based on clinically validated reasoning chains. HealthBranches supports both open-ended and multiple-choice question formats and uniquely includes the full reasoning path for each Q&A. Its structured design enables robust evaluation of LLMs' multi-step inference capabilities, including their performance in structured Retrieval-Augmented Generation (RAG) contexts. HealthBranches establishes a foundation for the development of more trustworthy, interpretable, and clinically reliable LLMs in high-stakes domains while also serving as a valuable resource for educational purposes.
title HealthBranches: Synthesizing Clinically-Grounded Question Answering Datasets via Decision Pathways
topic Computation and Language
Artificial Intelligence
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2508.07308