相关论文: MLLMEraser: Achieving Test-Time Unlearning in Mult…

This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts…

As Large Language Models (LLMs) demonstrate extensive capability in learning from documents, LLM unlearning becomes an increasingly important research area to address concerns of LLMs in terms of privacy, copyright, etc. A conventional LLM…

Large language models (LLMs) are prone to capturing biases from training corpus, leading to potential negative social impacts. Existing prompt-based debiasing methods exhibit instability due to their sensitivity to prompt changes, while…

Large language models are trained on massive corpora of web data, which may include private data, copyrighted material, factually inaccurate data, or data that degrades model performance. Eliminating the influence of such problematic…

Large language models inevitably retain sensitive information, defined as inputs that may induce harmful generations, due to training on massive web corpora, raising concerns for privacy and safety. Existing machine unlearning methods…

Traditional approaches to safety event analysis in autonomous systems have relied on complex machine learning models and extensive datasets for high accuracy and reliability. However, the advent of Multimodal Large Language Models (MLLMs)…

The paper demonstrate that simple adjustments of the fine-tuning recipes of multimodal large language models (MLLM) are sufficient to mitigate catastrophic forgetting. On visual question answering, we design a 2x2 experimental framework to…

The rapid advancement of Large Vision-Language Models (LVLMs) is increasingly accompanied by unauthorized scraping and training on multimodal web data, posing severe copyright and privacy risks to data owners. Existing countermeasures, such…

Large Language Models (LLMs) have achieved exceptional capabilities in open generation across various domains, yet they encounter difficulties with tasks that require intensive knowledge. To address these challenges, methods for integrating…

Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…

Multimodal large language models (MLLMs) play a pivotal role in advancing the quest for general artificial intelligence. However, achieving unified target for multimodal understanding and generation remains challenging due to optimization…

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) often exhibit undesirable behaviors, such as safety violations and hallucinations. Although inference-time steering offers a cost-effective way to adjust model behavior without updating its parameters, existing…

Multimodal Large Language Models (MLLMs) struggle with continual learning, often suffering from catastrophic forgetting when adapting to sequential tasks. We introduce a routing-based architecture that integrates new capabilities while…

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…

The success of Large Language Models (LLMs) has inspired the development of Multimodal Large Language Models (MLLMs) for unified understanding of vision and language. However, the increasing model size and computational complexity of…

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

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…

LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain…

Multimodal large language models (MLLMs) have shown success in vision-language tasks, but their ability to reason over complex educational materials remains largely untested. This work presents the first evaluation of state-of-the-art…