Related papers: Evaluating Copyright Takedown Methods for Language…

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 violate existing…

Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Existing defence…

Model editing has become an increasingly popular alternative for efficiently updating knowledge within language models. Current methods mainly focus on reliability, generalization, and locality, with many methods excelling across these…

This paper summarizes the current copyright related risks that Machine Learning (ML) and Artificial Intelligence (AI) systems (including Large Language Models --LLMs) incur. These risks affect different stakeholders: owners of the copyright…

How can we detect if copyrighted content was used in the training process of a language model, considering that the training data is typically undisclosed? We are motivated by the premise that a language model is likely to identify verbatim…

The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources. Despite substantial efforts devoted to data cleaning and curation, well-constructed LLMs have been…

Pre-training, which utilizes extensive and varied datasets, is a critical factor in the success of Large Language Models (LLMs) across numerous applications. However, the detailed makeup of these datasets is often not disclosed, leading to…

Large scale text-to-image generation models can memorize and reproduce their training dataset. Since the training dataset often contains copyrighted material, reproduction of training dataset poses a copyright infringement risk, which could…

Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. Due to the high cost of retraining from scratch, researchers attempt to employ machine unlearning to remove specific content…

Large Vision-Language Models (LVLMs), trained on web-scale data, risk memorizing and regenerating copyrighted visual content such as characters and logos, creating significant challenges. Machine unlearning offers a path to mitigate these…

As Large Language Models (LLMs) receive increasing attention and are being deployed across various domains, their potential risks, including generating harmful or biased content, producing unsupported claims, and exhibiting vulnerabilities…

In recent years, Large Language Models (LLMs) have gained significant popularity due to their ability to generate human-like text and their potential applications in various fields, such as Software Engineering. LLMs for Code are commonly…

Recent advances in Large Language Models (LLMs) have revolutionized code generation, leading to widespread adoption of AI coding tools by developers. However, LLMs can generate license-protected code without providing the necessary license…

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…

Large Language Models (LLMs) utilize extensive knowledge databases and show powerful text generation ability. However, their reliance on high-quality copyrighted datasets raises concerns about copyright infringements in generated texts.…

LLMs have been found to memorize training textual sequences and regurgitate verbatim said sequences during text generation time. This fact is known to be the cause of privacy and related (e.g., copyright) problems. Unlearning in LLMs then…

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks,…

Past literature has illustrated that language models (LMs) often memorize parts of training instances and reproduce them in natural language generation (NLG) processes. However, it is unclear to what extent LMs "reuse" a training corpus.…

As large language models (LLMs) are trained on increasingly opaque corpora, membership inference attacks (MIAs) have been proposed to audit whether copyrighted texts were used during training, despite growing concerns about their…

Large vision-language models (LVLMs) have achieved remarkable advancements in multimodal reasoning tasks. However, their widespread accessibility raises critical concerns about potential copyright infringement. Will LVLMs accurately…