UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shields-Menard, Sara, Reimers, Zach, Gardner, Joshua, Perry, David, Rios, Anthony
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908395903123456
author Shields-Menard, Sara
Reimers, Zach
Gardner, Joshua
Perry, David
Rios, Anthony
author_facet Shields-Menard, Sara
Reimers, Zach
Gardner, Joshua
Perry, David
Rios, Anthony
contents We describe our system for the ArchEHR-QA Shared Task on answering clinical questions using electronic health records (EHRs). Our approach uses large language models in two steps: first, to find sentences in the EHR relevant to a clinician's question, and second, to generate a short, citation-supported response based on those sentences. We use few-shot prompting, self-consistency, and thresholding to improve the sentence classification step to decide which sentences are essential. We compare several models and find that a smaller 8B model performs better than a larger 70B model for identifying relevant information. Our results show that accurate sentence selection is critical for generating high-quality responses and that self-consistency with thresholding helps make these decisions more reliable.
format Preprint
id arxiv_https___arxiv_org_abs_2506_05589
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting
Shields-Menard, Sara
Reimers, Zach
Gardner, Joshua
Perry, David
Rios, Anthony
Computation and Language
We describe our system for the ArchEHR-QA Shared Task on answering clinical questions using electronic health records (EHRs). Our approach uses large language models in two steps: first, to find sentences in the EHR relevant to a clinician's question, and second, to generate a short, citation-supported response based on those sentences. We use few-shot prompting, self-consistency, and thresholding to improve the sentence classification step to decide which sentences are essential. We compare several models and find that a smaller 8B model performs better than a larger 70B model for identifying relevant information. Our results show that accurate sentence selection is critical for generating high-quality responses and that self-consistency with thresholding helps make these decisions more reliable.
title UTSA-NLP at ArchEHR-QA 2025: Improving EHR Question Answering via Self-Consistency Prompting
topic Computation and Language
url https://arxiv.org/abs/2506.05589