Data Science with LLMs and Interpretable Models
This work addresses the challenge of making interpretable models more accessible and interactive for domain experts, though it is incremental as it applies existing LLM capabilities to a specific type of model.
The paper tackles the problem of enhancing the utility of interpretable models like Generalized Additive Models (GAMs) by integrating them with large language models (LLMs), showing that LLMs can effectively describe, interpret, and debug GAMs to enable tasks such as dataset summarization and model critique.
Recent years have seen important advances in the building of interpretable models, machine learning models that are designed to be easily understood by humans. In this work, we show that large language models (LLMs) are remarkably good at working with interpretable models, too. In particular, we show that LLMs can describe, interpret, and debug Generalized Additive Models (GAMs). Combining the flexibility of LLMs with the breadth of statistical patterns accurately described by GAMs enables dataset summarization, question answering, and model critique. LLMs can also improve the interaction between domain experts and interpretable models, and generate hypotheses about the underlying phenomenon. We release \url{https://github.com/interpretml/TalkToEBM} as an open-source LLM-GAM interface.