Saved in:
Bibliographic Details
Main Authors: Chouhan, Ashish, Gertz, Michael
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2506.19512
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911020446908416
author Chouhan, Ashish
Gertz, Michael
author_facet Chouhan, Ashish
Gertz, Michael
contents This paper presents the approach of our team called heiDS for the ArchEHR-QA 2025 shared task. A pipeline using a retrieval augmented generation (RAG) framework is designed to generate answers that are attributed to clinical evidence from the electronic health records (EHRs) of patients in response to patient-specific questions. We explored various components of a RAG framework, focusing on ranked list truncation (RLT) retrieval strategies and attribution approaches. Instead of using a fixed top-k RLT retrieval strategy, we employ a query-dependent-k retrieval strategy, including the existing surprise and autocut methods and two new methods proposed in this work, autocut* and elbow. The experimental results show the benefits of our strategy in producing factual and relevant answers when compared to a fixed-$k$.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19512
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle heiDS at ArchEHR-QA 2025: From Fixed-k to Query-dependent-k for Retrieval Augmented Generation
Chouhan, Ashish
Gertz, Michael
Computation and Language
This paper presents the approach of our team called heiDS for the ArchEHR-QA 2025 shared task. A pipeline using a retrieval augmented generation (RAG) framework is designed to generate answers that are attributed to clinical evidence from the electronic health records (EHRs) of patients in response to patient-specific questions. We explored various components of a RAG framework, focusing on ranked list truncation (RLT) retrieval strategies and attribution approaches. Instead of using a fixed top-k RLT retrieval strategy, we employ a query-dependent-k retrieval strategy, including the existing surprise and autocut methods and two new methods proposed in this work, autocut* and elbow. The experimental results show the benefits of our strategy in producing factual and relevant answers when compared to a fixed-$k$.
title heiDS at ArchEHR-QA 2025: From Fixed-k to Query-dependent-k for Retrieval Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2506.19512