Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models

Sebastian Bordt, Harsha Nori, Vanessa Cristiny Rodrigues Vasconcelos, Besmira Nushi, Rich Caruana

Research Area: Evaluation, LMs on diverse modalities and novel applications

Keywords: Memorization, Few-Shot Learning, Tabular Data

TL;DR: We compare the few-shot learning abilities of LLMs on tabular datasets that they have seen during training to datasets that were released after the cutoff date of the training data.

Abstract: While many have shown how Large Language Models (LLMs) can be applied to a diverse set of tasks, the critical issues of data contamination and memorization are often glossed over. In this work, we address this concern for tabular data. Specifically, we introduce a variety of different techniques to assess whether a language model has seen a tabular dataset during training. This investigation reveals that LLMs have memorized many popular tabular datasets verbatim. We then compare the few-shot learning performance of LLMs on datasets that were seen during training to the performance on datasets released after training. We find that LLMs perform better on datasets seen during training, indicating that memorization leads to overfitting. At the same time, LLMs show non-trivial performance on novel datasets and are surprisingly robust to data transformations. We then investigate the in-context statistical learning abilities of LLMs. While LLMs are significantly better than random at solving statistical classification problems, the sample efficiency of few-shot learning lags behind traditional statistical learning algorithms, especially as the dimension of the problem increases. This suggests that much of the observed few-shot performance on novel real-world datasets is due to the LLM's world knowledge. Overall, our results highlight the importance of testing whether an LLM has seen an evaluation dataset during pre-training. We release the https://github.com/interpretml/LLM-Tabular-Memorization-Checker Python package to test LLMs for memorization of tabular datasets.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 365