CopyShield is a benchmark that compares three copyright‑defense methods—contrastive decoding, Direct Preference Optimization (DPO), and activation intervention—across two large language models (LLaMA‑3.1‑8B and Mistral‑7B‑v0.3). The study uses controlled memorization of five public‑domain books to measure literal leakage, calibrated non‑literal leakage, utility, and degeneracy, finding that each intervention level yields distinct compliance‑utility trade‑offs. Results show contrastive decoding limits degeneracy but hits a suppression floor, DPO nearly eliminates literal leakage yet causes paraphrase‑loop degeneracy, and activation intervention blocks most non‑literal queries before generation, with human evaluation highlighting coherence and perceived copyright risk differences.
arXiv:2602.07120v3 Announce Type: replace Abstract: Language models (LMs) tend to memorize portions of their training data and emit verbatim spans. When the underlying sources are sensitive or copyri...
arXiv:2606. 06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use.
arXiv:2606. 05644v1 Announce Type: new Abstract: When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of retrieval augmentation.
arXiv:2607. 28862v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage.
arXiv:2602. 18733v2 Announce Type: replace Abstract: Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance.
arXiv:2606. 02822v1 Announce Type: cross Abstract: Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-registry authentication -- yet existing breach-and-attack-simulation (BAS) benchmarks report a single aggregate coverage number, hiding which family closes which threat.
Deep Contrastive Unlearning for Language Models (DeepCUT) is a framework that removes information from fine‑tuned language models by directly optimizing their latent space. It addresses the challenge of machine unlearning in black‑box models, which has been largely overlooked by previous work that only mitigated output effects. Experiments on real‑world datasets show that DeepCUT consistently outperforms baseline methods in both effectiveness and efficiency.
arXiv:2603. 18482v2 Announce Type: replace-cross Abstract: Standard decoding strategies for text generation, including top-$k$, nucleus sampling, and contrastive search, select tokens based on likelihood, restricting outputs to high-probability regions.
arXiv:2601.12075v2 Announce Type: replace Abstract: Language models used in retrieval-augmented settings must arbitrate between parametric knowledge stored in their weights and contextual information...
arXiv:2605. 07482v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous knowledge, without costly full retraining.
arXiv:2608. 01043v2 Announce Type: replace-cross Abstract: We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate (ASR).
arXiv:2606. 07996v1 Announce Type: cross Abstract: Pretraining is fundamental to the development of Large Language Models (LLMs), yet the opacity of pretraining data complicates model analysis and raises ethical, legal, and fairness concerns.