Mitigating Memorization In Language Models

• URL: http://arxiv.org/abs/2410.02159v1
• Date: Thu, 3 Oct 2024 02:53:51 GMT
• Title: Mitigating Memorization In Language Models
• Authors: Mansi Sakarvadia, Aswathy Ajith, Arham Khan, Nathaniel Hudson, Caleb Geniesse, Kyle Chard, Yaoqing Yang, Ian Foster, Michael W. Mahoney,
• Abstract summary: Language models (LMs) can "memorize" information, encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. We introduce TinyMem, a suite of small, computationally-efficient LMs for the rapid development and evaluation of memorization-mitigation methods. We show, in particular, that our proposed unlearning method BalancedSubnet outperforms other mitigation methods at removing memorized information while preserving performance on target tasks.
• Score: 37.899013074095336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that data. This ability to extract training data can be problematic, for example, when data are private or sensitive. In this work, we investigate methods to mitigate memorization: three regularizer-based, three finetuning-based, and eleven machine unlearning-based methods, with five of the latter being new methods that we introduce. We also introduce TinyMem, a suite of small, computationally-efficient LMs for the rapid development and evaluation of memorization-mitigation methods. We demonstrate that the mitigation methods that we develop using TinyMem can successfully be applied to production-grade LMs, and we determine via experiment that: regularizer-based mitigation methods are slow and ineffective at curbing memorization; fine-tuning-based methods are effective at curbing memorization, but overly expensive, especially for retaining higher accuracies; and unlearning-based methods are faster and more effective, allowing for the precise localization and removal of memorized information from LM weights prior to inference. We show, in particular, that our proposed unlearning method BalancedSubnet outperforms other mitigation methods at removing memorized information while preserving performance on target tasks.

Related papers

• Does Unlearning Truly Unlearn? A Black Box Evaluation of LLM Unlearning Methods [1.9799527196428242]
  Large language model unlearning aims to remove harmful information that LLMs have learnt to prevent their use for malicious purposes. LMU and RMU have been proposed as two methods for LLM unlearning, achieving impressive results on unlearning benchmarks.
  arXiv  Detail & Related papers  (2024-11-18T22:31:17Z)
• What Do Learning Dynamics Reveal About Generalization in LLM Reasoning? [83.83230167222852]
  We find that a model's generalization behavior can be effectively characterized by a training metric we call pre-memorization train accuracy. By connecting a model's learning behavior to its generalization, pre-memorization train accuracy can guide targeted improvements to training strategies.
  arXiv  Detail & Related papers  (2024-11-12T09:52:40Z)
• Scalability of memorization-based machine unlearning [2.5782420501870296]
  Machine unlearning (MUL) focuses on removing the influence of specific subsets of data from pretrained models. Memorization-based unlearning methods have been developed, demonstrating exceptional performance with respect to unlearning quality. We tackle these scalability challenges of state-of-the-art memorization-based MUL algorithms using a series of memorization-score proxies.
  arXiv  Detail & Related papers  (2024-10-21T21:18:39Z)
• 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)
• MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts [29.593170782882563]
  Large Language Models (LLMs) can memorize sensitive information, raising concerns about potential misuse. Previous practices face three key challenges: Utility, efficiency, and robustness. We propose MEOW, a gradient descent-based unlearning method.
  arXiv  Detail & Related papers  (2024-09-18T09:55:48Z)
• Detecting, Explaining, and Mitigating Memorization in Diffusion Models [49.438362005962375]
  We introduce a straightforward yet effective method for detecting memorized prompts by inspecting the magnitude of text-conditional predictions. Our proposed method seamlessly integrates without disrupting sampling algorithms, and delivers high accuracy even at the first generation step. Building on our detection strategy, we unveil an explainable approach that shows the contribution of individual words or tokens to memorization.
  arXiv  Detail & Related papers  (2024-07-31T16:13:29Z)
• PARMESAN: Parameter-Free Memory Search and Transduction for Dense Prediction Tasks [5.5127111704068374]
  This work addresses flexibility in deep learning by means of transductive reasoning. We propose PARMESAN, a scalable method which leverages a memory module for solving dense prediction tasks. Our method is compatible with commonly used architectures and canonically transfers to 1D, 2D, and 3D grid-based data.
  arXiv  Detail & Related papers  (2024-03-18T12:55:40Z)
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
  Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data. This process might suffer from privacy issues and violations of data protection regulations. We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
  arXiv  Detail & Related papers  (2023-10-31T03:35:59Z)
• Orthogonal Subspace Learning for Language Model Continual Learning [45.35861158925975]
  O-LoRA is a simple and efficient approach for continual learning in language models. Our method induces only marginal additional parameter costs and requires no user data storage for replay.
  arXiv  Detail & Related papers  (2023-10-22T02:23:44Z)
• A Memory Transformer Network for Incremental Learning [64.0410375349852]
  We study class-incremental learning, a training setup in which new classes of data are observed over time for the model to learn from. Despite the straightforward problem formulation, the naive application of classification models to class-incremental learning results in the "catastrophic forgetting" of previously seen classes. One of the most successful existing methods has been the use of a memory of exemplars, which overcomes the issue of catastrophic forgetting by saving a subset of past data into a memory bank and utilizing it to prevent forgetting when training future tasks.
  arXiv  Detail & Related papers  (2022-10-10T08:27:28Z)

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.