# Pruning as a Defense: Reducing Memorization in Large Language Models

arXiv: https://arxiv.org/abs/2502.15796 · HTML: https://mlsanity.com/paper/2502.15796/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [The Unreasonable Ineffectiveness of the Deeper Layers](https://mlsanity.com/paper/2403.17887/) (2024)
- [Task-Specific Skill Localization in Fine-tuned Language Models](https://mlsanity.com/paper/2302.06600/) (2023)
- [Dissecting Language Models: Machine Unlearning via Selective Pruning](https://mlsanity.com/paper/2403.01267/) (2024)
- [Investigating Hallucinations in Pruned Large Language Models for Abstractive Summarization](https://mlsanity.com/paper/2311.09335/) (2023)

## Built on by (most cited first, 3 of 3)

- [Mitigating Memorization Where It Happens](https://mlsanity.com/paper/2602.08901/) (2026)
- [What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models](https://mlsanity.com/paper/2601.20885/) (2026)
- [Bits and Memories: Measuring Verbatim Extraction Across LLM Quantization](https://mlsanity.com/paper/2607.25451/) (2026)

## Abstract (arXiv)

Large language models have been shown to memorize significant portions of their training data, which they can reproduce when appropriately prompted. This work investigates the impact of simple pruning techniques on this behavior. Our findings reveal that pruning effectively reduces the extent of memorization in LLMs, demonstrating its potential as a foundational approach for mitigating membership inference attacks.