arXiv Open Access 2024

Strong Copyright Protection for Language Models via Adaptive Model Fusion

Javier Abad Konstantin Donhauser Francesco Pinto Fanny Yang
Lihat Sumber

Abstrak

The risk of language models unintentionally reproducing copyrighted material from their training data has led to the development of various protective measures. In this paper, we propose model fusion as an effective solution to safeguard against copyright infringement. In particular, we introduce Copyright-Protecting Fusion (CP-Fuse), an algorithm that adaptively combines language models to minimize the reproduction of protected materials. CP-Fuse is inspired by the recently proposed Near-Access Free (NAF) framework and additionally incorporates a desirable balancing property that we demonstrate prevents the reproduction of memorized training data. Our results show that CP-Fuse significantly reduces the memorization of copyrighted content while maintaining high-quality text and code generation. Furthermore, we demonstrate how CP-Fuse can be integrated with other techniques for enhanced protection.

Topik & Kata Kunci

Penulis (4)

J

Javier Abad

K

Konstantin Donhauser

F

Francesco Pinto

F

Fanny Yang

Format Sitasi

Abad, J., Donhauser, K., Pinto, F., Yang, F. (2024). Strong Copyright Protection for Language Models via Adaptive Model Fusion. https://arxiv.org/abs/2407.20105

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2024
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓