相关论文: Obliviate: Efficient Unmemorization for Protecting…

Language models (LMs) are trained on vast amounts of text data, which may include private and copyrighted content. Data owners may request the removal of their data from a trained model due to privacy or copyright concerns. However, exactly…

Memorization in large-scale text-to-image diffusion models poses significant security and intellectual property risks, enabling adversarial attribute extraction and the unauthorized reproduction of sensitive or proprietary features. While…

Pre-trained Large Language Models (LLMs) have demonstrated remarkable capabilities but also pose risks by learning and generating copyrighted material, leading to significant legal and ethical concerns. In real-world scenarios, model owners…

The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on…

The exposure of large language models (LLMs) to copyrighted material during pre-training raises concerns about unintentional copyright infringement post deployment. This has driven the development of "copyright takedown" methods,…

Large Language Models have received significant attention due to their abilities to solve a wide range of complex tasks. However these models memorize a significant proportion of their training data, posing a serious threat when disclosed…

Multimodal Large Language Models (MLLMs) achieve impressive performance once optimized on massive datasets. Such datasets often contain sensitive or copyrighted content, raising significant data privacy concerns. Regulatory frameworks…

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…

Plaintiffs and defendants in copyright lawsuits over generative AI often make sweeping, opposing claims about the extent to which large language models (LLMs) memorize protected expression from books in their training data. We show that…

The current discourse on large language models (LLMs) and copyright largely takes a "behavioral" perspective, focusing on model outputs and evaluating whether they are substantially similar to training data. However, substantial similarity…

The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. However, while LLMs…

As Large Language Models (LLMs) continue to advance in their ability to write human-like text, a key challenge remains around their tendency to hallucinate generating content that appears factual but is ungrounded. This issue of…

Large Language Models (LLMs) increasingly leverage Federated Learning (FL) to utilize private, task-specific datasets for fine-tuning while preserving data privacy. However, while federated LLM frameworks effectively enable collaborative…

While large language models (LLMs) exhibit remarkable capabilities, they increasingly face demands to unlearn memorized privacy-sensitive, copyrighted, or harmful content. Existing unlearning methods primarily focus on \emph{single-shot}…

The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…

Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely on safety alignment strategies via RLHF, system prompts, and output filters to block verbatim…

We study how to perform unlearning, i.e. forgetting undesirable misbehaviors, on large language models (LLMs). We show at least three scenarios of aligning LLMs with human preferences can benefit from unlearning: (1) removing harmful…

Large language models (LLMs) have achieved impressive results in natural language processing but are prone to memorizing portions of their training data, which can compromise evaluation metrics, raise privacy concerns, and limit…

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, mixing web-scale data…

Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an…