# Data Science with LLMs and Interpretable Models

Source: [Data Science with LLMs and Interpretable Models](<https://www.sota2.com/research/paper/68fa72421e209131cea55587>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:30:07.706Z

Authors: Sebastian Bordt, Ben Lengerich, Harsha Nori, Rich Caruana

Published: 2024-02-22T12:04:15.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2402.14474>)

[PDF](<https://arxiv.org/pdf/2402.14474.pdf>)
