Prior Aware Memorization: An Efficient Metric for Distinguishing Memorization from Generalization in Large Language Models

• URL: http://arxiv.org/abs/2602.18733v1
• Date: Sat, 21 Feb 2026 06:31:17 GMT
• Title: Prior Aware Memorization: An Efficient Metric for Distinguishing Memorization from Generalization in Large Language Models
• Authors: Trishita Tiwari, Ari Trachtenberg, G. Edward Suh,
• Abstract summary: Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance.<n>Existing approaches to measuring memorization often conflate these phenomena, labeling outputs as memorized even when they arise from generalization over common patterns.<n>This work introduces Prior-Aware Memorization, a theoretically grounded, lightweight and training-free criterion for identifying genuine memorization in LLMs.
• Score: 9.915106680104268
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance. A central challenge in assessing this risk is distinguishing genuine memorization of training data from the generation of statistically common sequences. Existing approaches to measuring memorization often conflate these phenomena, labeling outputs as memorized even when they arise from generalization over common patterns. Counterfactual Memorization provides a principled solution by comparing models trained with and without a target sequence, but its reliance on retraining multiple baseline models makes it computationally expensive and impractical at scale. This work introduces Prior-Aware Memorization, a theoretically grounded, lightweight and training-free criterion for identifying genuine memorization in LLMs. The key idea is to evaluate whether a candidate suffix is strongly associated with its specific training prefix or whether it appears with high probability across many unrelated prompts due to statistical commonality. We evaluate this metric on text from the training corpora of two pre-trained models, LLaMA and OPT, using both long sequences (to simulate copyright risks) and named entities (to simulate PII leakage). Our results show that between 55% and 90% of sequences previously labeled as memorized are in fact statistically common. Similar findings hold for the SATML training data extraction challenge dataset, where roughly 40% of sequences exhibit common-pattern behavior despite appearing only once in the training data. These results demonstrate that low frequency alone is insufficient evidence of memorization and highlight the importance of accounting for model priors when assessing leakage.

Related papers

• Membership Inference Attacks from Causal Principles [24.370456956570873]
  We frame MIA evaluation as a causal inference problem, defining memorization as the causal effect of including a data point in the training set.<n>We propose practical estimators for multi-run, one-run, and zero-run regimes with non-asymptotic consistency guarantees.
  arXiv  Detail & Related papers  (2026-02-02T21:17:28Z)
• Retracing the Past: LLMs Emit Training Data When They Get Lost [18.852558767604823]
  memorization of training data in large language models poses significant privacy and copyright concerns.<n>This paper introduces Confusion-Inducing Attacks (CIA), a principled framework for extracting memorized data.
  arXiv  Detail & Related papers  (2025-10-27T03:48:24Z)
• Sequence-Level Leakage Risk of Training Data in Large Language Models [7.600279942640982]
  This work quantifies the risk of training data leakage from Large Language Models using sequence-level probabilities.<n>We re-analyze the effects of decoding schemes, model sizes, prefix lengths, partial sequence leakages, and token positions.
  arXiv  Detail & Related papers  (2024-12-15T20:27:45Z)
• Probably Approximately Precision and Recall Learning [60.00180898830079]
  A key challenge in machine learning is the prevalence of one-sided feedback.<n>We introduce a Probably Approximately Correct (PAC) framework in which hypotheses are set functions that map each input to a set of labels.<n>We develop new algorithms that learn from positive data alone, achieving optimal sample complexity in the realizable case.
  arXiv  Detail & Related papers  (2024-11-20T04:21:07Z)
• Detecting Training Data of Large Language Models via Expectation Maximization [62.28028046993391]
  We introduce EM-MIA, a novel membership inference method that iteratively refines membership scores and prefix scores via an expectation-maximization algorithm.<n> EM-MIA achieves state-of-the-art results on WikiMIA.
  arXiv  Detail & Related papers  (2024-10-10T03:31:16Z)
• Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens [1.2549198550400134]
  Large language models (LLMs) are extensively used, but there are concerns regarding privacy, security, and copyright due to their opaque training data. Current solutions to this problem leverage techniques explored in machine learning privacy such as Membership Inference Attacks (MIAs) We propose an adaptive pre-training data detection method which alleviates this reliance and effectively amplify the identification.
  arXiv  Detail & Related papers  (2024-07-30T23:43:59Z)
• 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)
• Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data [76.90128359866462]
  We introduce an extended concept of memorization, distributional memorization, which measures the correlation between the output probabilities and the pretraining data frequency.<n>This study demonstrates that memorization plays a larger role in simpler, knowledge-intensive tasks, while generalization is the key for harder, reasoning-based tasks.
  arXiv  Detail & Related papers  (2024-07-20T21:24:40Z)
• 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.