Memorization Sinks: Isolating Memorization during LLM Training

• URL: http://arxiv.org/abs/2507.09937v1
• Date: Mon, 14 Jul 2025 05:23:27 GMT
• Title: Memorization Sinks: Isolating Memorization during LLM Training
• Authors: Gaurav R. Ghosal, Pratyush Maini, Aditi Raghunathan,
• Abstract summary: Large language models are susceptible to memorizing repeated sequences, posing privacy and copyright concerns.<n>We propose a new paradigm of MemSinks that promotes isolation of memorization by design.<n>This is the first proof-of-concept on real data demonstrating that simultaneous generalization and isolation is achievable.
• Score: 20.682505625638203
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models are susceptible to memorizing repeated sequences, posing privacy and copyright concerns. A popular mitigation strategy is to remove memorized information from specific neurons post-hoc. However, such approaches have shown limited success so far. In a controlled setting, we show that the memorization of natural sequences (those that resemble linguistically plausible text) become mechanistically entangled with general language abilities, thereby becoming challenging to remove post-hoc. In this work, we put forward a new paradigm of MemSinks that promotes isolation of memorization by design. We leverage a sequence identifier that activates a unique set of memorization neurons for each sequence across repetitions. By analyzing the dynamics of learning and forgetting, we argue that MemSinks facilitates isolation of memorized content, making it easier to remove without compromising general language capabilities. We implement MemSinks at the billion-parameter and billion-token scale, and observe both effective isolation and strong generalization. To our knowledge, this is the first proof-of-concept on real data demonstrating that simultaneous generalization and isolation is achievable. We open-source our code at http://github.com/grghosal/MemSinks.

Related papers

• Rethinking Memorization Measures and their Implications in Large Language Models [14.04812038444537]
  We study whether memorization can be avoided when optimally learning a language, and whether the privacy threat posed by memorization is exaggerated or not.<n>Re-examine existing privacy-focused measures of memorization, namely recollection-based and counterfactual memorization, along with a newly proposed contextual memorization.<n>Experimenting on 18 LLMs from 6 families and multiple formal languages of different entropy, we show that (a) memorization measures disagree on memorization order of varying frequent strings, (b) optimal learning of a language cannot avoid partial memorization of training strings, and (c) improved learning decreases contextual and counterfactual memorization but increases recollection-
  arXiv  Detail & Related papers  (2025-07-20T00:33:19Z)
• Memorize or Generalize? Evaluating LLM Code Generation with Evolved Questions [33.58518352911762]
  Large Language Models (LLMs) are known to exhibit a memorization phenomenon in code generation.<n>In this paper, we investigate this phenomenon by designing three evolution strategies to create variants: mutation, paraphrasing, and code-rewriting.<n>As expected, as supervised fine-tuning goes on, the memorization score rises before overfitting, suggesting more severe memorization.
  arXiv  Detail & Related papers  (2025-03-04T05:39:24Z)
• Unlocking Memorization in Large Language Models with Dynamic Soft Prompting [66.54460367290146]
  Large language models (LLMs) have revolutionized natural language processing (NLP) tasks such as summarization, question answering, and translation. LLMs pose significant security risks due to their tendency to memorize training data, leading to potential privacy breaches and copyright infringement. We propose a novel method for estimating LLM memorization using dynamic, prefix-dependent soft prompts.
  arXiv  Detail & Related papers  (2024-09-20T18:56:32Z)
• Demystifying Verbatim Memorization in Large Language Models [67.49068128909349]
  Large Language Models (LLMs) frequently memorize long sequences verbatim, often with serious legal and privacy implications. We develop a framework to study verbatim memorization in a controlled setting by continuing pre-training from Pythia checkpoints with injected sequences. We find that (1) non-trivial amounts of repetition are necessary for verbatim memorization to happen; (2) later (and presumably better) checkpoints are more likely to memorize verbatim sequences, even for out-of-distribution sequences.
  arXiv  Detail & Related papers  (2024-07-25T07:10:31Z)
• SoK: Memorization in General-Purpose Large Language Models [25.448127387943053]
  Large Language Models (LLMs) are advancing at a remarkable pace, with myriad applications under development. LLMs can memorize short secrets in the training data, but can also memorize concepts like facts or writing styles that can be expressed in text in many different ways. We propose a taxonomy for memorization in LLMs that covers verbatim text, facts, ideas and algorithms, writing styles, distributional properties, and alignment goals.
  arXiv  Detail & Related papers  (2023-10-24T14:25:53Z)
• Exploring Memorization in Fine-tuned Language Models [53.52403444655213]
  We conduct the first comprehensive analysis to explore language models' memorization during fine-tuning across tasks. Our studies with open-sourced and our own fine-tuned LMs across various tasks indicate that memorization presents a strong disparity among different fine-tuning tasks. We provide an intuitive explanation of this task disparity via sparse coding theory and unveil a strong correlation between memorization and attention score distribution.
  arXiv  Detail & Related papers  (2023-10-10T15:41:26Z)
• Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy [91.98116450958331]
  We argue that verbatim memorization definitions are too restrictive and fail to capture more subtle forms of memorization. Specifically, we design and implement an efficient defense that perfectly prevents all verbatim memorization. We conclude by discussing potential alternative definitions and why defining memorization is a difficult yet crucial open question for neural language models.
  arXiv  Detail & Related papers  (2022-10-31T17:57:55Z)
• Quantifying Memorization Across Neural Language Models [61.58529162310382]
  Large language models (LMs) have been shown to memorize parts of their training data, and when prompted appropriately, they will emit the memorized data verbatim. This is undesirable because memorization violates privacy (exposing user data), degrades utility (repeated easy-to-memorize text is often low quality), and hurts fairness (some texts are memorized over others). We describe three log-linear relationships that quantify the degree to which LMs emit memorized training data.
  arXiv  Detail & Related papers  (2022-02-15T18:48:31Z)
• Counterfactual Memorization in Neural Language Models [91.8747020391287]
  Modern neural language models that are widely used in various NLP tasks risk memorizing sensitive information from their training data. An open question in previous studies of language model memorization is how to filter out "common" memorization. We formulate a notion of counterfactual memorization which characterizes how a model's predictions change if a particular document is omitted during training.
  arXiv  Detail & Related papers  (2021-12-24T04:20:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.