Version-aware question answering over living oncology guidelines
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Living clinical guidelines revise recommendations as evidence emerges, so an AI answer can be faithful to a real guideline and still be out of date. Here we examine this failure using ASCOBench, 288 unique questions in 96 three-turn conversations grounded in versioned American Society of Clinical Oncology (ASCO) breast and prostate cancer guidelines, with oncologist-reviewed reference answers. Oncologists corrected one in four version-sensitive answers drafted by a frontier model, against fewer than one in ten factual ones. Across the guideline corpus, 19 recommendations changed between versions, seven of them reversals, yet only 1 of 14 superseded documents states that it has been replaced. With a strong model, retrieval over several guideline versions made stale answers four times more frequent than answering without retrieval. SentryLine, a verification-first system, lowered incorrect answers to 4.2-5.2% from 9.7-22.9% for baselines across three models. Recognizing change before a guideline declares it remains an open problem.
Article activity feed
-
Version-aware question answering over living oncology guidelines https://www.biorxiv.org/content/10.64898/2026.10.04.756483v1
-
Version-aware question answering over living oncology guidelines https://www.biorxiv.org/content/10.64898/2026.10.04.756483v1
-