Related papers: OFFSIDE: Benchmarking Unlearning Misinformation in…
In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation, ensuring that models forget not only specific training samples but also related implicit knowledge. To this end, we begin by…
Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity raises growing concerns about privacy leakage, toxicity…
Machine Learning (ML) models have been shown to potentially leak sensitive information, thus raising privacy concerns in ML-driven applications. This inspired recent research on removing the influence of specific data samples from a trained…
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…
There have been a couple of studies showing that attempting to erase multilingual knowledge using only English data is insufficient for multilingual LLMs. However, their analyses remain highly performance-oriented. In this paper, we switch…
Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…
Large language models (LLMs) have recently revolutionized language processing tasks but have also brought ethical and legal issues. LLMs have a tendency to memorize potentially private or copyrighted information present in the training…
Machine unlearning (MU) aims to remove the influence of particular data points from the learnable parameters of a trained machine learning model. This is a crucial capability in light of data privacy requirements, trustworthiness, and…
Machine unlearning offers a promising solution to privacy and safety concerns in large language models (LLMs) by selectively removing targeted knowledge while preserving utility. However, current methods are highly sensitive to downstream…
While numerous machine unlearning (MU) methods have recently been developed with promising results in erasing the influence of forgotten data, classes, or concepts, they are also highly vulnerable-for example, simple fine-tuning can…
Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models. Unlike autoregressive models, which generate text sequentially, MDLMs generate text by…
Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwanted behaviors from the diverse and sensitive nature of their…
Machine unlearning for large language models often faces a privacy dilemma in which strict constraints prohibit sharing either the server's parameters or the client's forget set. To address this dual non-disclosure constraint, we propose…
Machine unlearning has emerged as a prevalent technical solution for selectively removing unwanted knowledge absorbed during pre-training, without requiring full retraining. While recent unlearning techniques can effectively remove…
With the implementation of personal data privacy regulations, the field of machine learning (ML) faces the challenge of the "right to be forgotten". Machine unlearning has emerged to address this issue, aiming to delete data and reduce its…
Multimodal Large Language Models (MLLMs) achieve remarkable capabilities but can inadvertently memorize privacy-sensitive information. Although existing unlearning methods can remove such knowledge, they fail to achieve benign forgetting…
Machine unlearning (MU) enables the removal of selected training data from trained models, to address privacy compliance, security, and liability issues in recommender systems. Existing MU benchmarks poorly reflect real-world recommender…
Machine unlearning is an emerging field that selectively removes specific data samples from a trained model. This capability is crucial for addressing privacy concerns, complying with data protection regulations, and correcting errors or…
Machine unlearning aims to remove unwanted information from a model, but many methods are inefficient for LLMs with large numbers of parameters or fail to fully remove the intended information without degrading performance on knowledge that…
Multimodal Misinformation Recognition has become an urgent task with the emergence of huge multimodal fake content on social media platforms. Previous studies mainly focus on complex feature extraction and fusion to learn discriminative…