Related papers: Unified Parameter-Efficient Unlearning for LLMs
Parameter efficient learning methods (PERMs) have recently gained significant attention as they provide an efficient way for pre-trained language models (PLMs) to adapt to a downstream task. However, these conclusions are mostly drawn from…
With increasing privacy concerns on data, recent studies have made significant progress using federated learning (FL) on privacy-sensitive natural language processing (NLP) tasks. Much literature suggests fully fine-tuning pre-trained…
Large language models (LLMs) have revolutionized natural language processing by achieving state-of-the-art performance across various tasks. Recently, their effectiveness as embedding models has gained attention, marking a paradigm shift…
Large language models (LLMs) with one or more fine-tuning phases have become a necessary step to unlock various capabilities, enabling LLMs to follow natural language instructions or align with human preferences. However, it carries the…
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}…
In recent years, Large Language Models (LLMs) through Transformer structures have dominated many machine learning tasks, especially text processing. However, these models require massive amounts of data for training and induce high resource…
The current literature on memorization in Natural Language Models, especially Large Language Models (LLMs), poses severe security and privacy risks, as models tend to memorize personally identifying information (PIIs) from training data. We…
Despite the strong capabilities of Large Language Models (LLMs) to acquire knowledge from their training corpora, the memorization of sensitive information in the corpora such as copyrighted, biased, and private content has led to ethical…
Generative models such as Large Language Models (LLM) and Multimodal Large Language models (MLLMs) trained on massive web corpora can memorize and disclose individuals' confidential and private data, raising legal and ethical concerns.…
Recent progress in Machine Unlearning (MU) has introduced solutions for the selective removal of private or sensitive information encoded within deep neural networks. Nonetheless, MU for Multimodal Large Language Models (MLLMs) remains in…
Large language model unlearning has become a critical challenge in ensuring safety and controlled model behavior by removing undesired data-model influences from the pretrained model while preserving general utility. Significant recent…
Finetuning language models (LMs) is crucial for adapting the models to downstream data and tasks. However, full finetuning is usually costly. Existing work, such as parameter-efficient finetuning (PEFT), often focuses on \textit{how to…
Despite advances in Preference Alignment (PA) for Large Language Models (LLMs), mainstream methods like Reinforcement Learning with Human Feedback (RLHF) face notable challenges. These approaches require high-quality datasets of positive…
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…
This survey delves into the realm of Parameter-Efficient Fine-Tuning (PEFT) within the context of Foundation Models (FMs). PEFT, a cost-effective fine-tuning technique, minimizes parameters and computational complexity while striving for…
The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…
Large language models (LLMs) risk retaining sensitive, copyrighted, or harmful information from their training data. Entity-level unlearning addresses this issue by removing all knowledge of a specific entity while preserving the model's…
The Unlearning Sensitive Content from Large Language Models task aims to remove targeted datapoints from trained models while minimally affecting their general knowledge. In our work, we leverage parameter-efficient, gradient-based…
The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B…
Jailbreaking attacks can enable Large Language Models (LLMs) to bypass the safeguard and generate harmful content. Existing jailbreaking defense methods have failed to address the fundamental issue that harmful knowledge resides within the…