When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910063281569792 |
|---|---|
| author | Li, Yubo Krishnan, Ramayya Padman, Rema |
| author_facet | Li, Yubo Krishnan, Ramayya Padman, Rema |
| contents | Patient education materials for solid-organ transplantation vary substantially across U.S. centers, yet no systematic method exists to quantify this heterogeneity at scale. We introduce a framework that grounds the same patient questions in different centers' handbooks using retrieval-augmented language models and compares the resulting answers using a five-label consistency taxonomy. Applied to 102 handbooks from 23 centers and 1,115 benchmark questions, the framework quantifies heterogeneity across four dimensions: question, topic, organ, and center. We find that 20.8% of non-absent pairwise comparisons exhibit clinically meaningful divergence, concentrated in condition monitoring and lifestyle topics. Coverage gaps are even more prominent: 96.2% of question-handbook pairs miss relevant content, with reproductive health at 95.1% absence. Center-level divergence profiles are stable and interpretable, where heterogeneity reflects systematic institutional differences, likely due to patient diversity. These findings expose an information gap in transplant patient education materials, with document-grounded medical question answering highlighting opportunities for content improvement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_21460 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models Li, Yubo Krishnan, Ramayya Padman, Rema Information Retrieval Artificial Intelligence Patient education materials for solid-organ transplantation vary substantially across U.S. centers, yet no systematic method exists to quantify this heterogeneity at scale. We introduce a framework that grounds the same patient questions in different centers' handbooks using retrieval-augmented language models and compares the resulting answers using a five-label consistency taxonomy. Applied to 102 handbooks from 23 centers and 1,115 benchmark questions, the framework quantifies heterogeneity across four dimensions: question, topic, organ, and center. We find that 20.8% of non-absent pairwise comparisons exhibit clinically meaningful divergence, concentrated in condition monitoring and lifestyle topics. Coverage gaps are even more prominent: 96.2% of question-handbook pairs miss relevant content, with reproductive health at 95.1% absence. Center-level divergence profiles are stable and interpretable, where heterogeneity reflects systematic institutional differences, likely due to patient diversity. These findings expose an information gap in transplant patient education materials, with document-grounded medical question answering highlighting opportunities for content improvement. |
| title | When Documents Disagree: Measuring Institutional Variation in Transplant Guidance with Retrieval-Augmented Language Models |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2603.21460 |