zkLLM: Zero Knowledge Proofs for Large Language Models

arXiv:2404.16109v1 Announce Type: cross
Abstract: The recent surge in artificial intelligence (AI), characterized by the prominence of large language models (LLMs), has ushered in fundamental transformations across the globe. However, alongside these advancements, concerns surrounding the legitimacy of LLMs have grown, posing legal challenges to their extensive applications. Compounding these concerns, the parameters of LLMs are often treated as intellectual property, restricting direct investigations.
In this study, we address a fundamental challenge within the realm of AI legislation: the need …

advancements applications artificial artificial intelligence arxiv challenges cs.cr cs.lg intelligence knowledge language language models large legal llms prominence zero knowledge zero knowledge proofs