SOURCE-LINKED INTELLIGENCE

CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Large language models can reproduce memorized text verbatim, yet copyright defenses are usually evaluated under incompatible protocols. We introduce CopyShield, a controlled benchmark comparing three representative defenses at distinct intervention levels: contrastive decoding (output), Direct Preference Optimization (behavioral), and activation intervention (representation). We evaluate CopyShield on two model families, LLaMA-3.1-8B and Mistral-7B-v0.3, using controlled memorization over five public-domain books and a shared protocol measuring literal leakage, calibrated non-literal leakage,

Read original source ↗ Open in workspace

recordType

paper

region

Global