Language models may memorize more than just facts, including entire chunks of
texts seen during training. Fair use exemptions to copyright laws typically
allow for limited use of copyrighted material without permission from the
copyright holder, but typically for extraction of information from copyrighted
materials, rather than {\em verbatim} reproduction. This work explores the
issue of copyright violations and large language models through the lens of
verbatim memorization, focusing on possible redistribution of copyrighted text.
We present experiments with a range of language models over a collection of
popular books and coding problems, providing a conservative characterization of
the extent to which language models can redistribute these materials. Overall,
this research highlights the need for further examination and the potential
impact on future developments in natural language processing to ensure
adherence to copyright regulations. Code is at
https://github.com/coastalcph/CopyrightLLMs.

本研究通过对语言模型的逐字记忆进行探索，重点关注版权文字的再分发可能性，通过对一系列热门图书和编码问题进行实验，提供了个人估计的语言模型再分发这些材料的程度。总体而言，本研究强调了进一步研究的必要性，以及对版权法规遵守的潜在影响和未来自然语言处理发展的潜在影响。

侵权与大型语言模型

Copyright Violations and Large Language Models

Studying data memorization in neural language models helps us understand the
risks (e.g., to privacy or copyright) associated with models regurgitating
training data, and aids in the evaluation of potential countermeasures. Many
prior works -- and some recently deployed defenses -- focus on "verbatim
memorization", defined as a model generation that exactly matches a substring
from the training set. 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 based on Bloom
filters that perfectly prevents all verbatim memorization. And yet, we
demonstrate that this "perfect" filter does not prevent the leakage of training
data. Indeed, it is easily circumvented by plausible and minimally modified
"style-transfer" prompts -- and in some cases even the non-modified original
prompts -- to extract memorized information. For example, instructing the model
to output ALL-CAPITAL texts bypasses memorization checks based on verbatim
matching. We conclude by discussing potential alternative definitions and why
defining memorization is a difficult yet crucial open question for neural
language models.

通过 Bloom 过滤器与 ALL-CAPITAL text 跨越数据记忆的问题，阐述了训练数据的记忆问题与风险，并讨论了针对神经语言模型中数据记忆的潜在替代定义和本质难题。