Large scale text-to-image generation models can memorize and reproduce their training dataset. Since the training dataset often contains copyrighted material, reproduction of training dataset poses a copyright infringement risk, which could result in legal liabilities and financial losses for both the AI user and the developer. The current works explores the potential of chain-of-thought and task instruction prompting in reducing copyrighted content generation. To this end, we present a formulation that combines these two techniques with two other copyright mitigation strategies: a) negative prompting, and b) prompt re-writing. We study the generated images in terms their similarity to a copyrighted image and their relevance of the user input. We present numerical experiments on a variety of models and provide insights on the effectiveness of the aforementioned techniques for varying model complexity.
@article{arxiv.2512.15442,
title = {Copyright Infringement Risk Reduction via Chain-of-Thought and Task Instruction Prompting},
author = {Neeraj Sarna and Yuanyuan Li and Michael von Gablenz},
journal= {arXiv preprint arXiv:2512.15442},
year = {2025}
}