相关论文: Erasing Without Remembering: Implicit Knowledge Fo…

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…

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these…

Foundation models have transformed multimedia analysis by enabling robust and transferable representations across diverse modalities and tasks. However, their static deployment conflicts with growing societal and regulatory demands --…

VLMs trained on web-scale data retain sensitive and copyrighted visual concepts that deployment may require removing. Training-based unlearning methods share a structural flaw: fine-tuning on a narrow forget set degrades general…

As AI models are trained on ever-expanding datasets, the ability to remove the influence of specific data from trained models has become essential for privacy protection and regulatory compliance. Unlearning addresses this challenge by…

While many recent methods aim to unlearn or remove knowledge from pretrained models, seemingly erased knowledge often persists and can be recovered in various ways. Because large foundation models are far from interpretable, understanding…

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…

Large language models often fail to satisfy formatting instructions when they must simultaneously perform demanding tasks. We study this behaviour through a prospective memory inspired lens from cognitive psychology, using a controlled…

Generative models such as Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) trained on massive datasets can lead them to memorize and inadvertently reveal sensitive information, raising ethical and privacy concerns.…

Large Language Models' knowledge of how to perform cyber-security attacks, create bioweapons, and manipulate humans poses risks of misuse. Previous work has proposed methods to unlearn this knowledge. Historically, it has been unclear…

With the passage of the Right to Be Forgotten (RTBF) regulations and the scaling up of language model training datasets, research on model unlearning in large language models (LLMs) has become more crucial. Before the era of LLMs, machine…

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…

Machine unlearning aims to remove specific information, e.g. sensitive or undesirable content, from large language models (LLMs) while preserving overall performance. We propose an inference-time unlearning algorithm that uses contrastive…

Large Language Models (LLMs) inherently encode a wealth of knowledge within their parameters through pre-training on extensive corpora. While prior research has delved into operations on these parameters to manipulate the underlying…

Pretrained large language models (LLMs) have revolutionized natural language processing (NLP) tasks such as summarization, question answering, and translation. However, LLMs pose significant security risks due to their tendency to memorize…

Language models retain a significant amount of world knowledge from their pre-training stage. This allows knowledgeable models to be applied to knowledge-intensive tasks prevalent in information retrieval, such as ranking or question…

Large language models (LLMs) inherently absorb harmful knowledge, misinformation, and personal data during pretraining on large-scale web corpora, with no native mechanism for selective removal. While machine unlearning offers a principled…

Large language models (LLMs) acquire a large amount of knowledge through pre-training on vast and diverse corpora. While this endows LLMs with strong capabilities in generation and reasoning, it amplifies risks associated with sensitive,…

The growing concern over training data privacy has elevated the "Right to be Forgotten" into a critical requirement, thereby raising the demand for effective Machine Unlearning. However, existing unlearning approaches commonly suffer from a…

Large Vision-Language Models (LVLMs) can recognize individuals in images and disclose sensitive personal information about them, raising critical privacy concerns. Machine unlearning aims to remove such knowledge from the model. However,…