Had enough of experts? Quantitative knowledge retrieval from large language models
This addresses the need for efficient data analysis tools in fields like healthcare and environmental science, though it appears incremental by applying LLMs to existing Bayesian workflows.
The paper tackled the problem of using large language models (LLMs) for quantitative knowledge retrieval, specifically for eliciting prior distributions in Bayesian models and imputing missing data, resulting in improved predictive accuracy and reduced data requirements across diverse datasets.
Large language models (LLMs) have been extensively studied for their abilities to generate convincing natural language sequences, however their utility for quantitative information retrieval is less well understood. Here we explore the feasibility of LLMs as a mechanism for quantitative knowledge retrieval to aid two data analysis tasks: elicitation of prior distributions for Bayesian models and imputation of missing data. We introduce a framework that leverages LLMs to enhance Bayesian workflows by eliciting expert-like prior knowledge and imputing missing data. Tested on diverse datasets, this approach can improve predictive accuracy and reduce data requirements, offering significant potential in healthcare, environmental science and engineering applications. We discuss the implications and challenges of treating LLMs as 'experts'.