Researchllmmodel memorizationcopyrightmodel auditing
Researchers Extract Copyrighted Books From Production Language Models
|
9.0
In a preprint and following a 90-day disclosure window that ended Dec. 9, 2025, Stanford and Yale researchers showed they could extract large portions of copyrighted books from production LLMs including Claude 3.7 Sonnet, GPT-4.1, Gemini 2.5 Pro, and Grok 3, with recall rates up to 95.8 percent for Harry Potter. The results show memorization can bypass vendor guardrails and may affect ongoing copyright litigation and vendor mitigation strategies.
Scoring Rationale
High cross-industry relevance and actionable findings, limited by reliance on a single preprint and pending peer review.
Practice with real Logistics & Shipping data
90 SQL & Python problems · 15 industry datasets
Used by DS/ML engineers at top companies
High-Value Overnight OrdersEasyDelivered International ShipmentsMediumOn-Time Delivery Rate by CarrierHard
250 free problems · No credit card
See all Logistics & Shipping problems
