cs.LGNov 5, 2026

An Information Bottleneck for Post-hoc Memorization Mitigation in LLMs

Authors: Dina EL Zein, Shashi Kumar, James Henderson

Organizations: Idiap Research Institute, Switzerland · EPFL, Switzerland

Abstract

Recent studies have shown that large language models (LLMs) can memorize and reproduce copyrighted training data, raising serious privacy and intellectual property concerns. In this work, we investigate whether memorization can be mitigated without modifying or retraining the underlying model through an information bottleneck. We propose a modular plug-and-play framework that inserts a nonparametric variational information bottleneck (NVIB) between a frozen LLM backbone and its language modeling head. By compressing the final hidden representations before token prediction, the proposed bottleneck aims to preserve general linguistic knowledge while filtering out highly specific memorized sequences. We evaluate our approach on memorization extraction tasks involving book passages and on standard language modeling benchmarks to measure the trade-off between memorization reduction and downstream utility. Our experiments show that the NVIB layer substantially reduces extractability while maintaining competitive performance on benchmark tasks. These results suggest that adding an information bottleneck offers a practical and architecture agnostic direction for post-hoc memorization mitigation in pretrained LLMs.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Mitigating Memorization In Language Models

    Oct 3, 2024Mansi Sakarvadia, Aswathy Ajith, Arham Khan +6Memorization in Language ModelsLLM Fine-Tuning

  2. Mitigating Memorization Where It Happens

    Feb 9, 2026Xuanqi Zhang, Haoyang Shang, Xiaoxiao LiMemorization in Language ModelsPrivacy Leakage in Language Models

  3. A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models

    Feb 21, 2026Trishita Tiwari, Ari Trachtenberg, G. Edward SuhMemorization in Language ModelsLLM Auditing