The Files are in the Computer: Copyright, Memorization, and Generative AI

• URL: http://arxiv.org/abs/2404.12590v4
• Date: Mon, 11 Nov 2024 19:59:04 GMT
• Title: The Files are in the Computer: Copyright, Memorization, and Generative AI
• Authors: A. Feder Cooper, James Grimmelmann,
• Abstract summary: The New York Times's copyright lawsuit against OpenAI and Microsoft alleges OpenAI's GPT models have "memorized" NYT articles. These debates are clouded by ambiguities over the nature of "memorization" We draw on the technical literature to provide a precise definition of memorization.
• Score: 2.1178416840822027
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The New York Times's copyright lawsuit against OpenAI and Microsoft alleges OpenAI's GPT models have "memorized" NYT articles. Other lawsuits make similar claims. But parties, courts, and scholars disagree on what memorization is, whether it is taking place, and what its copyright implications are. These debates are clouded by ambiguities over the nature of "memorization." We attempt to bring clarity to the conversation. We draw on the technical literature to provide a firm foundation for legal discussions, providing a precise definition of memorization: a model has "memorized" a piece of training data when (1) it is possible to reconstruct from the model (2) a near-exact copy of (3) a substantial portion of (4) that piece of training data. We distinguish memorization from "extraction" (user intentionally causes a model to generate a near-exact copy), from "regurgitation" (model generates a near-exact copy, regardless of user intentions), and from "reconstruction" (the near-exact copy can be obtained from the model by any means). Several consequences follow. (1) Not all learning is memorization. (2) Memorization occurs when a model is trained; regurgitation is a symptom not its cause. (3) A model that has memorized training data is a "copy" of that training data in the sense used by copyright. (4) A model is not like a VCR or other general-purpose copying technology; it is better at generating some types of outputs (possibly regurgitated ones) than others. (5) Memorization is not a phenomenon caused by "adversarial" users bent on extraction; it is latent in the model itself. (6) The amount of training data that a model memorizes is a consequence of choices made in training. (7) Whether or not a model that has memorized actually regurgitates depends on overall system design. In a very real sense, memorized training data is in the model--to quote Zoolander, the files are in the computer.

Related papers

• Measuring Non-Adversarial Reproduction of Training Data in Large Language Models [71.55350441396243]
  We quantify the overlap between model responses and pretraining data when responding to natural and benign prompts. We find that up to 15% of the text output by popular conversational language models overlaps with snippets from the Internet. While appropriate prompting can reduce non-adversarial reproduction on average, we find that mitigating worst-case reproduction of training data requires stronger defenses.
  arXiv  Detail & Related papers  (2024-11-15T14:55:01Z)
• Rethinking LLM Memorization through the Lens of Adversarial Compression [93.13830893086681]
  Large language models (LLMs) trained on web-scale datasets raise substantial concerns regarding permissible data usage. One major question is whether these models "memorize" all their training data or they integrate many data sources in some way more akin to how a human would learn and synthesize information. We propose the Adversarial Compression Ratio (ACR) as a metric for assessing memorization in LLMs.
  arXiv  Detail & Related papers  (2024-04-23T15:49:37Z)
• 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)
• AI Model Disgorgement: Methods and Choices [127.54319351058167]
  We introduce a taxonomy of possible disgorgement methods that are applicable to modern machine learning systems. We investigate the meaning of "removing the effects" of data in the trained model in a way that does not require retraining from scratch.
  arXiv  Detail & Related papers  (2023-04-07T08:50:18Z)
• 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)
• Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models [64.22311189896888]
  We study exact memorization in causal and masked language modeling, across model sizes and throughout the training process. Surprisingly, we show that larger models can memorize a larger portion of the data before over-fitting and tend to forget less throughout the training process.
  arXiv  Detail & Related papers  (2022-05-22T07:43:50Z)
• Do Language Models Plagiarize? [22.02731537718498]
  We investigate whether language models memorize but also plagiarize training samples when generating artificial texts. Our findings support that they, especially GPT-2, reuse particular pieces of texts from the training corpus with or without obfuscation. Our work implies that future research on neural language models should take precautions to avoid models plagiarizing their training datasets.
  arXiv  Detail & Related papers  (2022-03-15T03:11:11Z)
• 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)
• Dataset Inference: Ownership Resolution in Machine Learning [18.248121977353506]
  knowledge contained in stolen model's training set is what is common to all stolen copies. We introduce $dataset$ $inference, the process of identifying whether a suspected model copy has private knowledge from the original model's dataset. Experiments on CIFAR10, SVHN, CIFAR100 and ImageNet show that model owners can claim with confidence greater than 99% that their model (or dataset as a matter of fact) was stolen.
  arXiv  Detail & Related papers  (2021-04-21T18:12:18Z)

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.