Copyright Violations and Large Language Models

Antonia Karamolegkou, Jiaang Li, Li Zhou, Anders Søgaard

Submission Type: Regular Short Paper

Submission Track: Ethics in NLP

Submission Track 2: Theme Track: Large Language Models and the Future of NLP

Keywords: language models, copyright, NLP, LLMs

Abstract: 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.

Submission Number: 5571