Saved in:
Bibliographic Details
Main Authors: Pronesti, Massimiliano, Bettencourt-Silva, Joao, Flanagan, Paul, Pascale, Alessandra, Redmond, Oisin, Belz, Anya, Hou, Yufang
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.06186
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913867349622784
author Pronesti, Massimiliano
Bettencourt-Silva, Joao
Flanagan, Paul
Pascale, Alessandra
Redmond, Oisin
Belz, Anya
Hou, Yufang
author_facet Pronesti, Massimiliano
Bettencourt-Silva, Joao
Flanagan, Paul
Pascale, Alessandra
Redmond, Oisin
Belz, Anya
Hou, Yufang
contents Extracting scientific evidence from biomedical studies for clinical research questions (e.g., Does stem cell transplantation improve quality of life in patients with medically refractory Crohn's disease compared to placebo?) is a crucial step in synthesising biomedical evidence. In this paper, we focus on the task of document-level scientific evidence extraction for clinical questions with conflicting evidence. To support this task, we create a dataset called CochraneForest, leveraging forest plots from Cochrane systematic reviews. It comprises 202 annotated forest plots, associated clinical research questions, full texts of studies, and study-specific conclusions. Building on CochraneForest, we propose URCA (Uniform Retrieval Clustered Augmentation), a retrieval-augmented generation framework designed to tackle the unique challenges of evidence extraction. Our experiments show that URCA outperforms the best existing methods by up to 10.3% in F1 score on this task. However, the results also underscore the complexity of CochraneForest, establishing it as a challenging testbed for advancing automated evidence synthesis systems.
format Preprint
id arxiv_https___arxiv_org_abs_2505_06186
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Query-driven Document-level Scientific Evidence Extraction from Biomedical Studies
Pronesti, Massimiliano
Bettencourt-Silva, Joao
Flanagan, Paul
Pascale, Alessandra
Redmond, Oisin
Belz, Anya
Hou, Yufang
Computation and Language
Artificial Intelligence
Extracting scientific evidence from biomedical studies for clinical research questions (e.g., Does stem cell transplantation improve quality of life in patients with medically refractory Crohn's disease compared to placebo?) is a crucial step in synthesising biomedical evidence. In this paper, we focus on the task of document-level scientific evidence extraction for clinical questions with conflicting evidence. To support this task, we create a dataset called CochraneForest, leveraging forest plots from Cochrane systematic reviews. It comprises 202 annotated forest plots, associated clinical research questions, full texts of studies, and study-specific conclusions. Building on CochraneForest, we propose URCA (Uniform Retrieval Clustered Augmentation), a retrieval-augmented generation framework designed to tackle the unique challenges of evidence extraction. Our experiments show that URCA outperforms the best existing methods by up to 10.3% in F1 score on this task. However, the results also underscore the complexity of CochraneForest, establishing it as a challenging testbed for advancing automated evidence synthesis systems.
title Query-driven Document-level Scientific Evidence Extraction from Biomedical Studies
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.06186