Skewed Memorization in Large Language Models: Quantification and Decomposition

• URL: http://arxiv.org/abs/2502.01187v1
• Date: Mon, 03 Feb 2025 09:23:53 GMT
• Title: Skewed Memorization in Large Language Models: Quantification and Decomposition
• Authors: Hao Li, Di Huang, Ziyu Wang, Amir M. Rahmani,
• Abstract summary: Memorization in Large Language Models (LLMs) poses privacy and security risks, as models may unintentionally reproduce sensitive or copyrighted data. This paper examines memorization in supervised fine-tuning (SFT), exploring its relationships with training duration, dataset size, and inter-sample similarity.
• Score: 23.097554469918357
• License:
• Abstract: Memorization in Large Language Models (LLMs) poses privacy and security risks, as models may unintentionally reproduce sensitive or copyrighted data. Existing analyses focus on average-case scenarios, often neglecting the highly skewed distribution of memorization. This paper examines memorization in LLM supervised fine-tuning (SFT), exploring its relationships with training duration, dataset size, and inter-sample similarity. By analyzing memorization probabilities over sequence lengths, we link this skewness to the token generation process, offering insights for estimating memorization and comparing it to established metrics. Through theoretical analysis and empirical evaluation, we provide a comprehensive understanding of memorization behaviors and propose strategies to detect and mitigate risks, contributing to more privacy-preserving LLMs.

Related papers

• Detecting Memorization in Large Language Models [0.0]
  Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data. Traditional methods for detecting memorization rely on output probabilities or loss functions. We introduce an analytical method that precisely detects memorization by examining neuron activations within the LLM.
  arXiv  Detail & Related papers  (2024-12-02T00:17:43Z)
• A Geometric Framework for Understanding Memorization in Generative Models [11.263296715798374]
  Recent work has shown that deep generative models can be capable of memorizing and reproducing training datapoints when deployed. These findings call into question the usability of generative models, especially in light of the legal and privacy risks brought about by memorization. We propose the manifold memorization hypothesis (MMH), a geometric framework which leverages the manifold hypothesis into a clear language in which to reason about memorization.
  arXiv  Detail & Related papers  (2024-10-31T18:09:01Z)
• Measuring memorization through probabilistic discoverable extraction [19.4511858341881]
  Large language models (LLMs) are susceptible to memorizing training data. Current methods to measure memorization rates of LLMs rely on single-sequence greedy sampling.
  arXiv  Detail & Related papers  (2024-10-25T11:37:04Z)
• Undesirable Memorization in Large Language Models: A Survey [5.659933808910005]
  We present a Systematization of Knowledge (SoK) on the topic of memorization in Large Language Models (LLMs) Memorization is the effect that a model tends to store and reproduce phrases or passages from the training data. We discuss the metrics and methods used to measure memorization, followed by an analysis of the factors that contribute to memorization phenomenon.
  arXiv  Detail & Related papers  (2024-10-03T16:34:46Z)
• 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. We show 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)
• ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods [56.073335779595475]
  We propose ReCaLL (Relative Conditional Log-Likelihood), a novel membership inference attack (MIA) ReCaLL examines the relative change in conditional log-likelihoods when prefixing target data points with non-member context. We conduct comprehensive experiments and show that ReCaLL achieves state-of-the-art performance on the WikiMIA dataset.
  arXiv  Detail & Related papers  (2024-06-23T00:23:13Z)
• Cycles of Thought: Measuring LLM Confidence through Stable Explanations [53.15438489398938]
  Large language models (LLMs) can reach and even surpass human-level accuracy on a variety of benchmarks, but their overconfidence in incorrect responses is still a well-documented failure mode. We propose a framework for measuring an LLM's uncertainty with respect to the distribution of generated explanations for an answer.
  arXiv  Detail & Related papers  (2024-06-05T16:35:30Z)
• 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)
• Mitigating Approximate Memorization in Language Models via Dissimilarity Learned Policy [0.0]
  Large Language models (LLMs) are trained on large amounts of data. LLMs showed to memorize parts of the training data and emit those data verbatim when an adversary prompts appropriately.
  arXiv  Detail & Related papers  (2023-05-02T15:53:28Z)
• Exploring Memorization in Adversarial Training [58.38336773082818]
  We investigate the memorization effect in adversarial training (AT) for promoting a deeper understanding of capacity, convergence, generalization, and especially robust overfitting. We propose a new mitigation algorithm motivated by detailed memorization analyses.
  arXiv  Detail & Related papers  (2021-06-03T05:39:57Z)

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.