相关论文: Machine Unlearning in Large Language Models

The alignment of large language models (LLMs) aims to ensure their outputs adhere to human values, ethical standards, and legal norms. Traditional alignment methods often rely on resource-intensive fine-tuning (FT), which may suffer from…

Recent advances in large language models (LLMs) have opened new opportunities for recommender systems by enabling rich semantic understanding and reasoning about user interests and item attributes. However, as privacy regulations tighten,…

Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents. LLMs have been trained on a vast corpus of texts from various sources; despite the best…

This paper investigates using knowledge editing techniques to detoxify Large Language Models (LLMs). We construct a benchmark, SafeEdit, which covers nine unsafe categories with various powerful attack prompts and equips comprehensive…

Large language models deployed in sensitive applications increasingly require the ability to unlearn specific knowledge, such as user requests, copyrighted materials, or outdated information, without retraining from scratch to ensure…

This study reveals a previously unexplored vulnerability in the safety alignment of Large Language Models (LLMs). Existing aligned LLMs predominantly respond to unsafe queries with refusals, which often begin with a fixed set of prefixes…

Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically…

Large language Models (LLMs) have demonstrated remarkable skills across various domains. Understanding the mechanisms behind their abilities and implementing controls over them is becoming increasingly important for developing better…

Large language models (LLMs) exhibit powerful capabilities but risk memorizing sensitive personally identifiable information (PII) from their training data, posing significant privacy concerns. While machine unlearning techniques aim to…

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…

Safety guard models that detect malicious queries aimed at large language models (LLMs) are essential for ensuring the secure and responsible deployment of LLMs in real-world applications. However, deploying existing safety guard models…

The undesired memorization of sensitive information by Large Language Models (LLMs) has emphasized the need for safety mechanisms that can regulate model behavior. This has led to the development of machine unlearning techniques that enable…

Unlearning has emerged as a critical capability for large language models (LLMs) to support data privacy, regulatory compliance, and ethical AI deployment. Recent techniques often rely on obfuscation by injecting incorrect or irrelevant…

Large language models (LLMs) and generative AI have played a transformative role in computer research and applications. Controversy has arisen as to whether these models output copyrighted data, which can occur if the data the models are…

Instruction-following large language models (LLMs), such as ChatGPT, have become widely popular among everyday users. However, these models inadvertently disclose private, sensitive information to their users, underscoring the need for…

With the rapid progress of diffusion-based content generation, significant efforts are being made to unlearn harmful or copyrighted concepts from pretrained diffusion models (DMs) to prevent potential model misuse. However, it is observed…

Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its true effectiveness against privacy attacks remains unclear.…

Large language models (LLMs) have transformed the way computers understand and process human language, but using them effectively across different organizations remains still difficult. When organizations work together to improve LLMs, they…

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…

Short video platforms are evolving rapidly, making the identification of inappropriate content increasingly critical. Existing approaches typically train separate and small classification models for each type of issue, which requires…