Van Allen

Abstract: Despite high performance on clinical benchmarks, large language models may reach correct conclusions through faulty reasoning, a failure

South Carolina leaders saw fit to adapt a withholding incentive for hybrid and remote office work scenarios. Photo of Columbia, South Carolina, by Sean Pavone: Getty Images

Integrated knowledge translation (iKT) still relies on static reports, presentations, and manuscripts that cannot adapt to decision-makers' evolving questions. Retrieval-augmented large language models (LLMs) can add a secure, auditable conversational layer over curated program outputs and selected research materials, enabling rapid, traceable synthesis between meetings and across portfolios. Treating these tools as governed infrastructure, with mandatory provenance, privacy protections, transparent documentation, and equity-by-design, could help reduce friction in evidence exchange and shorten the lag between knowledge creation and use.

Abstract Purpose: Computational pathology has emerged as an attractive option for improving risk stratification in prostate cancer (PCa), but

By Tiffany E. Payne, P. Barrett Morris, and Nader Raja, Moore & Van Allen.

Large language models (LLMs) show strong performance on clinical benchmarks, yet their reasoning reliability in real-world oncology care remains unclear.