# Data Science with LLMs and Interpretable Models

arXiv: https://arxiv.org/abs/2402.14474 · HTML: https://mlsanity.com/paper/2402.14474/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 24 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 10 of 10)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Faith and Fate: Limits of Transformers on Compositionality](https://mlsanity.com/paper/2305.18654/) (2023)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [Generalized and Scalable Optimal Sparse Decision Trees](https://mlsanity.com/paper/2006.08690/) (2020)
- [From Shapley Values to Generalized Additive Models and back](https://mlsanity.com/paper/2209.04012/) (2022)
- [TabRet: Pre-training Transformer-based Tabular Models for Unseen Columns](https://mlsanity.com/paper/2303.15747/) (2023)
- [LLMs Understand Glass-Box Models, Discover Surprises, and Suggest Repairs](https://mlsanity.com/paper/2308.01157/) (2023)

## Built on by (most cited first, 8 of 8)

- [Data Interpreter: An LLM Agent For Data Science](https://mlsanity.com/paper/2402.18679/) (2024)
- [Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models](https://mlsanity.com/paper/2404.06209/) (2024)
- [A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future](https://mlsanity.com/paper/2412.14056/) (2024)
- [BIASINSPECTOR: Detecting Bias in Structured Data through LLM Agents](https://mlsanity.com/paper/2504.04855/) (2025)
- [Navigating the Rashomon Effect: How Personalization Can Help Adjust Interpretable Machine Learning Models to Individual Users](https://mlsanity.com/paper/2505.07100/) (2025)
- [The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Data](https://mlsanity.com/paper/2508.02765/) (2025)
- [Lazy or Efficient? Towards Accessible Eye-Tracking Event Detection Using LLMs](https://mlsanity.com/paper/2604.13243/) (2026)
- [Can Conversational XAI Improve User Performance? An Experimental Study](https://mlsanity.com/paper/2605.20439/) (2026)

## Abstract (arXiv)

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 urlhttps://github.com/interpretml/TalkToEBM as an open-source LLM-GAM interface.