← all papers · overview

Huref: Human-readable Fingerprint For Large Language Models

Abstract

Protecting the copyright of large language models (LLMs) has become crucial due to their resource-intensive training and accompanying carefully designed licenses. However, identifying the original base model of an LLM is challenging due to potential parameter alterations. In this study, we introduce HuRef, a human-readable fingerprint for LLMs that uniquely identifies the base model without interf

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).