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guidelines revise recommendations as evidence emerges, so an AI answer can be faithful to a real guideline and still be out of date.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...
Tampu Ravi Kumar, Anirudh Iyengar Kaniyar Narayana Iyengar, Muhammad Ali Khan et al.· bioRxiv· 0 citations
Systematic reviews condense clinical trials into evidence tables, yet clinicians can interrogate these tables only through database queries, and many questions concern attributes that the table does not record, such as a drug’s target class or a harmonised endpoint. Here we introduce FD-SCoPE, a language-model framewor...
M. Choudhury, Suparno Roy Chowdhury, S. Sahoo et al.· bioRxiv· 0 citations
SENTRYLINE is presented, a living guideline-aware clinical question answering system that retrieves guideline passages through a vectorless hierarchical RAG pipeline and returns a role-specific answer with inline citations, factual and temporal verification reports, and drift detection notes that surface when a guideli...
Tampu Ravi Kumar, Gaurav Najpande, Muhammad Ali Khan et al.· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
