Related papers: Less is More: Geometric Unlearning for LLMs with M…
Language models can retain dangerous knowledge and skills even after extensive safety fine-tuning, posing both misuse and misalignment risks. Recent studies show that even specialized unlearning methods can be easily reversed. To address…
Machine unlearning for large language models (LLMs) aims to remove targeted knowledge while preserving general capability. In this paper, we recast LLM unlearning as an asymmetric two-task problem: retention is the primary objective and…
Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ensuring alignment and thus safe use. However, accurately and…
Due to increasing privacy regulations and regulatory compliance, Machine Unlearning (MU) has become essential. The goal of unlearning is to remove information related to a specific class from a model. Traditional approaches achieve exact…
Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous knowledge, without costly full retraining. Most existing methods require a retain set of…
Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining. Current unlearning methods share a common weakness: erased concepts return when the…
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…
The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…
When introducing Large Language Models (LLMs) into industrial applications, such as healthcare and education, the risk of generating harmful content becomes a significant challenge. While existing machine unlearning methods can erase…
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 --…
Federated Learning (FL) offers a promising paradigm for training Large Language Models (LLMs) in a decentralized manner while preserving data privacy and minimizing communication overhead. This survey examines recent advancements in…
Machine unlearning, the study of efficiently removing the impact of specific training instances on a model, has garnered increased attention in recent years due to regulatory guidelines such as the \emph{Right to be Forgotten}. Achieving…
Unlearning algorithms aim to remove deleted data's influence from trained models at a cost lower than full retraining. However, prior guarantees of unlearning in literature are flawed and don't protect the privacy of deleted records. We…
Unlearning in Large Language Models (LLMs) is crucial for protecting private data and removing harmful knowledge. Most existing approaches rely on fine-tuning to balance unlearning efficiency with general language capabilities. However,…
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) 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…
Recent work has demonstrated that finetuning is a promising approach to 'unlearn' concepts from large language models. However, finetuning can be expensive, as it requires both generating a set of examples and running iterations 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…
As large language models (LLMs) are applied across diverse domains, the ability to selectively unlearn specific information is becoming increasingly essential. For instance, LLMs are expected to selectively provide confidential information…
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…