Copyright-Protected Language Generation via Adaptive Model Fusion

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Abad, Javier, Donhauser, Konstantin, Pinto, Francesco, Yang, Fanny
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915055063269376
author Abad, Javier
Donhauser, Konstantin
Pinto, Francesco
Yang, Fanny
author_facet Abad, Javier
Donhauser, Konstantin
Pinto, Francesco
Yang, Fanny
contents The risk of language models reproducing copyrighted material from their training data has led to the development of various protective measures. Among these, inference-time strategies that impose constraints via post-processing have shown promise in addressing the complexities of copyright regulation. However, they often incur prohibitive computational costs or suffer from performance trade-offs. To overcome these limitations, we introduce Copyright-Protecting Model Fusion (CP-Fuse), a novel approach that combines models trained on disjoint sets of copyrighted material during inference. In particular, CP-Fuse adaptively aggregates the model outputs to minimize the reproduction of copyrighted content, adhering to a crucial balancing property that prevents the regurgitation of memorized data. Through extensive experiments, we show that CP-Fuse significantly reduces the reproduction of protected material without compromising the quality of text and code generation. Moreover, its post-hoc nature allows seamless integration with other protective measures, further enhancing copyright safeguards. Lastly, we show that CP-Fuse is robust against common techniques for extracting training data.
format Preprint
id arxiv_https___arxiv_org_abs_2412_06619
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Copyright-Protected Language Generation via Adaptive Model Fusion
Abad, Javier
Donhauser, Konstantin
Pinto, Francesco
Yang, Fanny
Machine Learning
Computation and Language
Cryptography and Security
The risk of language models reproducing copyrighted material from their training data has led to the development of various protective measures. Among these, inference-time strategies that impose constraints via post-processing have shown promise in addressing the complexities of copyright regulation. However, they often incur prohibitive computational costs or suffer from performance trade-offs. To overcome these limitations, we introduce Copyright-Protecting Model Fusion (CP-Fuse), a novel approach that combines models trained on disjoint sets of copyrighted material during inference. In particular, CP-Fuse adaptively aggregates the model outputs to minimize the reproduction of copyrighted content, adhering to a crucial balancing property that prevents the regurgitation of memorized data. Through extensive experiments, we show that CP-Fuse significantly reduces the reproduction of protected material without compromising the quality of text and code generation. Moreover, its post-hoc nature allows seamless integration with other protective measures, further enhancing copyright safeguards. Lastly, we show that CP-Fuse is robust against common techniques for extracting training data.
title Copyright-Protected Language Generation via Adaptive Model Fusion
topic Machine Learning
Computation and Language
Cryptography and Security
url https://arxiv.org/abs/2412.06619