# Elephants Never Forget: Testing Language Models for Memorization of Tabular Data

arXiv: https://arxiv.org/abs/2403.06644 · HTML: https://mlsanity.com/paper/2403.06644/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 34 references that are in the map.
- First posted on arXiv 11 Mar 2024.

## Builds on (most cited first, 25 of 25)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Datasheets for Datasets](https://mlsanity.com/paper/1803.09010/) (2018)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (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)
- [Retiring Adult: New Datasets for Fair Machine Learning](https://mlsanity.com/paper/2108.04884/) (2021)
- [Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models](https://mlsanity.com/paper/2212.03860/) (2022)
- [Language Models are Realistic Tabular Data Generators](https://mlsanity.com/paper/2210.06280/) (2022)
- [TabLLM: Few-shot Classification of Tabular Data with Large Language Models](https://mlsanity.com/paper/2210.10723/) (2022)
- [Membership Inference Attacks against Language Models via Neighbourhood Comparison](https://mlsanity.com/paper/2305.18462/) (2023)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models](https://mlsanity.com/paper/2205.10770/) (2022)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks](https://mlsanity.com/paper/2206.06565/) (2022)
- [Speak, Memory: An Archaeology of Books Known to ChatGPT/GPT-4](https://mlsanity.com/paper/2305.00118/) (2023)
- [An Interpretable Model with Globally Consistent Explanations for Credit Risk](https://mlsanity.com/paper/1811.12615/) (2018)
- [Adapting Pretrained Language Models for Solving Tabular Prediction Problems in the Electronic Health Record](https://mlsanity.com/paper/2303.14920/) (2023)

## Built on by (most cited first, 19 of 19)

- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [Preference Leakage: A Contamination Problem in LLM-as-a-judge](https://mlsanity.com/paper/2502.01534/) (2025)
- [Retrieval & Fine-Tuning for In-Context Tabular Models](https://mlsanity.com/paper/2406.05207/) (2024)
- [A Survey on Data Contamination for Large Language Models](https://mlsanity.com/paper/2502.14425/) (2025)
- [Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation](https://mlsanity.com/paper/2406.14644/) (2024)
- [Take Caution in Using LLMs as Human Surrogates: Scylla Ex Machina](https://mlsanity.com/paper/2410.19599/) (2024)
- [Differentially Private Tabular Data Synthesis using Large Language Models](https://mlsanity.com/paper/2406.01457/) (2024)
- [Large Language Models Engineer Too Many Simple Features For Tabular Data](https://mlsanity.com/paper/2410.17787/) (2024)
- [Training an LLM-as-a-Judge Model: Pipeline, Insights, and Practical Lessons](https://mlsanity.com/paper/2502.02988/) (2025)
- [Clinical Insights: A Comprehensive Review of Language Models in Medicine](https://mlsanity.com/paper/2408.11735/) (2024)
- ["Oh LLM, I'm Asking Thee, Please Give Me a Decision Tree": Zero-Shot Decision Tree Induction and Embedding with Large Language Models](https://mlsanity.com/paper/2409.18594/) (2024)
- [Gradient Boosting Trees and Large Language Models for Tabular Data Few-Shot Learning](https://mlsanity.com/paper/2411.04324/) (2024)
- [A text-to-tabular approach to generate synthetic patient data using LLMs](https://mlsanity.com/paper/2412.05153/) (2024)
- [Realizing LLMs' Causal Potential Requires Science-Grounded, Novel Benchmarks](https://mlsanity.com/paper/2510.16530/) (2025)
- [Large Language Models Memorize Sensor Datasets! Implications on Human Activity Recognition Research](https://mlsanity.com/paper/2406.05900/) (2024)
- [Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboard](https://mlsanity.com/paper/2505.13421/) (2025)
- [Establishing Trustworthy LLM Evaluation via Shortcut Neuron Analysis](https://mlsanity.com/paper/2506.04142/) (2025)
- [FAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigations](https://mlsanity.com/paper/2506.11635/) (2025)
- [Probing Memorization of Tabular In-Context Learning](https://mlsanity.com/paper/2606.31208/) (2026)

## Abstract (arXiv)

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. Starting with simple qualitative tests for whether an LLM knows the names and values of features, we introduce a variety of different techniques to assess the degrees of contamination, including statistical tests for conditional distribution modeling and four tests that identify memorization. Our investigation reveals that LLMs are pre-trained on many popular tabular datasets. This exposure can lead to invalid performance evaluation on downstream tasks because the LLMs have, in effect, been fit to the test set. Interestingly, we also identify a regime where the language model reproduces important statistics of the data, but fails to reproduce the dataset verbatim. On these datasets, although seen during training, good performance on downstream tasks might not be due to overfitting. Our findings underscore the need for ensuring data integrity in machine learning tasks with LLMs. To facilitate future research, we release an open-source tool that can perform various tests for memorization urlhttps://github.com/interpretml/LLM-Tabular-Memorization-Checker.