Almanac: Retrieval-Augmented Language Models for Clinical Medicine
This addresses the issue of unreliable AI in clinical decision-making for healthcare professionals, though it is incremental as it builds on existing retrieval-augmented methods.
The authors tackled the problem of large language models generating incorrect or toxic statements in clinical medicine by developing Almanac, a retrieval-augmented framework, which increased factuality by a mean of 18% on a dataset of 130 clinical scenarios.
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.