LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs
This work addresses the need for automated model interpretation and repair in data science, particularly for domain-specific applications like healthcare, though it appears incremental as it applies LLMs to existing interpretable models.
The paper tackles the problem of automating data science tasks by showing that large language models (LLMs) can effectively work with interpretable models like Generalized Additive Models (GAMs) to detect anomalies, explain them, and suggest repairs, as demonstrated in healthcare examples.
We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components. By adopting a hierarchical approach to reasoning, LLMs can provide comprehensive model-level summaries without ever requiring the entire model to fit in context. This approach enables LLMs to apply their extensive background knowledge to automate common tasks in data science such as detecting anomalies that contradict prior knowledge, describing potential reasons for the anomalies, and suggesting repairs that would remove the anomalies. We use multiple examples in healthcare to demonstrate the utility of these new capabilities of LLMs, with particular emphasis on Generalized Additive Models (GAMs). Finally, we present the package $\texttt{TalkToEBM}$ as an open-source LLM-GAM interface.