paper-with-me

홈 › Papers

Exploring Memorization and Copyright Violation in Frontier LLMs: A Study of the New York Times v. OpenAI 2023 Lawsuit

2024-12-09 · Joshua Freeman, Chloe Rippe, Edoardo Debenedetti, Maksym Andriushchenko

Copyright infringement in frontier LLMs has received much attention recently due to the New York Times v. OpenAI lawsuit, filed in December 2023. The New York Times claims that GPT-4 has infringed its copyrights by reproducing articles for use in LLM training and by memorizing the inputs, thereby publicly displaying them in LLM outputs. Our work aims to measure the propensity of OpenAI's LLMs to exhibit verbatim memorization in its outputs relative to other LLMs, specifically focusing on news articles. We discover that both GPT and Claude models use refusal training and output filters to prevent verbatim output of the memorized articles. We apply a basic prompt template to bypass the refusal training and show that OpenAI models are currently less prone to memorization elicitation than models from Meta, Mistral, and Anthropic. We find that as models increase in size, especially beyond 100 billion parameters, they demonstrate significantly greater capacity for memorization. Our findings have practical implications for training: more attention must be placed on preventing verbatim memorization in very large models. Our findings also have legal significance: in assessing the relative memorization capacity of OpenAI's LLMs, we probe the strength of The New York Times's copyright infringement claims and OpenAI's legal defenses, while underscoring issues at the intersection of generative AI, law, and policy.

📄 PDF Abstract BibTeX arXiv:2412.06370

Code (0)

등록된 구현이 없습니다.

Tasks

ArticlesMemorization

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Position-Wise Feed-Forward Layer 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

LLMs and Memorization: On Quality and Specificity of Copyright Compliance

2024-05-28 · Felix B Mueller, Rebekka Görge, Anna K Bernzen, Janna C Pirk 외

Memorization in large language models (LLMs) is a growing concern. LLMs have been shown to easily reproduce parts of their training data, including copyrighted work. This is an important problem to solve, as it may viola…

HallucinationMemorizationSpecificityText Matching

Copyright Violations and Large Language Models

2023-10-20 · Antonia Karamolegkou, Jiaang Li, Li Zhou, Anders Søgaard

Language models may memorize more than just facts, including entire chunks of texts seen during training. Fair use exemptions to copyright laws typically allow for limited use of copyrighted material without permission f…

Memorization

Unconsciously Forget: Mitigating Memorization; Without Knowing What is being Memorized

2025-12-10 · Er Jin, Yang Zhang, Yongli Mou, Yanfei Dong 외 arxiv

Recent advances in generative models have demonstrated an exceptional ability to produce highly realistic images. However, previous studies show that generated images often resemble the training data, and this problem be…

Exploring Memorization in Fine-tuned Language Models

2023-10-10 · Shenglai Zeng, Yaxin Li, Jie Ren, Yiding Liu 외

Large language models (LLMs) have shown great capabilities in various tasks but also exhibited memorization of training data, raising tremendous privacy and copyright concerns. While prior works have studied memorization…

Memorization

Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks

2025-05-19 · YiXuan Xu, Antoine Bosselut, Imanol Schlag

Large language models are known to memorize parts of their training data, posing risk of copyright violations. To systematically examine this risk, we pretrain language models (1B/3B/8B) from scratch on 83B tokens, mixin…

AttributeMemorization