heiDS at ArchEHR-QA 2025: from fixed-k to query-dependent-k for retrieval augmented generation
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...
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Chapter/Article Conference Paper |
| Lingua: | inglese |
| Pubblicazione: |
August 2025
|
| In: |
The 24th BioNLP Workshop and shared tasks - proceedings of the 24th Workshop on Biomedical Language Processing (shared tasks)
Year: 2025, Pages: 50-61 |
| DOI: | 10.18653/v1/2025.bionlp-share.6 |
| Accesso online: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.18653/v1/2025.bionlp-share.6 Verlag, lizenzpflichtig, Volltext: https://aclanthology.org/2025.bionlp-share.6/ 
|
| Note sull'autore: | Ashish Chouhan and Michael Gertz |
| Riassunto: | 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. |
|---|---|
| Descrizione del documento: | Gesehen am 06.07.2026 |
| Descrizione fisica: | Online Resource |
| ISBN: | 9798891762763 |
| DOI: | 10.18653/v1/2025.bionlp-share.6 |