Almanac: Retrieval-Augmented Language Models for Clinical Medicine

TL;DR

Almanac is a retrieval-augmented large language model designed for clinical medicine, significantly improving factual accuracy and safety in medical guideline and treatment recommendations through retrieval capabilities.

Contribution

This work introduces Almanac, a novel retrieval-augmented language model tailored for clinical medicine, enhancing factuality and safety in medical decision support.

Findings

18% increase in factuality across specialties

Improved completeness and safety of recommendations

Significant performance gains with retrieval augmentation

Abstract

Large-language models have recently demonstrated impressive zero-shot capabilities in a variety of natural language tasks such as summarization, dialogue generation, and question-answering. Despite many promising applications in clinical medicine, adoption of these models in real-world settings has been largely limited by their tendency to generate incorrect and sometimes even toxic statements. In this study, we develop Almanac, a large language model framework augmented with retrieval capabilities for medical guideline and treatment recommendations. Performance on a novel dataset of clinical scenarios (n = 130) evaluated by a panel of 5 board-certified and resident physicians demonstrates significant increases in factuality (mean of 18% at p-value < 0.05) across all specialties, with improvements in completeness and safety. Our results demonstrate the potential for large language models to be effective tools in the clinical decision-making process, while also emphasizing the importance of careful testing and deployment to mitigate their shortcomings.