Related papers: Multi-Objective Large Language Model Unlearning
While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particular, since models may store unsafe knowledge internally,…
The composition of training data mixtures is critical for effectively training large language models (LLMs), as it directly impacts their performance on downstream tasks. Our goal is to identify an optimal data mixture to specialize an LLM…
Multi-objective optimization is a common problem in practical applications, and multi-objective evolutionary algorithm (MOEA) is considered as one of the effective methods to solve these problems. However, their randomness sometimes…
We propose a method of moments (MoM) algorithm for training large-scale implicit generative models. Moment estimation in this setting encounters two problems: it is often difficult to define the millions of moments needed to learn the model…
Continual learning (CL), which requires the model to learn multiple tasks sequentially, is crucial for large language models (LLMs). Recently, low-rank adaptation~(LoRA), one of the most representative parameter-efficient fine-tuning (PEFT)…
Catastrophic forgetting is a significant challenge in continual learning, in which a model loses prior knowledge when it is fine-tuned on new tasks. This problem is particularly critical for large language models (LLMs) undergoing continual…
Training and fine-tuning large language models (LLMs) come with challenges related to memory and computational requirements due to the increasing size of the model weights and the optimizer states. Various techniques have been developed to…
Out-of-distribution (OOD) detection is essential for reliable and trustworthy machine learning. Recent multi-modal OOD detection leverages textual information from in-distribution (ID) class names for visual OOD detection, yet it currently…
Large language models (LLMs) have revolutionized lots of fields of research. Although it is well-known that fine-tuning is essential for enhancing the capabilities of LLMs, existing research suggests that there is potential redundancy in…
The undesired memorization of sensitive information by Large Language Models (LLMs) has emphasized the need for safety mechanisms that can regulate model behavior. This has led to the development of machine unlearning techniques that enable…
Recent advances in Multimodal Large Language Models (MLLMs) have enhanced their versatility as they integrate a growing number of modalities. Considering the heavy cost of training MLLMs, it is efficient to reuse the existing ones and…
As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. Machine Unlearning (MU), as an effective strategy for forgetting specific knowledge in training data, has been widely…
Multi-Objective Reinforcement Learning (MORL) presents significant challenges and opportunities for optimizing multiple objectives in Large Language Models (LLMs). We introduce a MORL taxonomy and examine the advantages and limitations of…
Catastrophic forgetting remains a formidable obstacle to building an omniscient model in large language models (LLMs). Despite the pioneering research on task-level forgetting in LLM fine-tuning, there is scant focus on forgetting during…
Humans can retain old knowledge while learning new information, but Large Language Models (LLMs) often suffer from catastrophic forgetting when post-pretrained or supervised fine-tuned (SFT) on domain-specific data. Moreover, for Multimodal…
Robust unlearning is crucial for safely deploying large language models (LLMs) in environments where data privacy, model safety, and regulatory compliance must be ensured. Yet the task is inherently challenging, partly due to difficulties…
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…
Multimodal large language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations,…
Large language models (LLMs) often struggle with knowledge intensive NLP tasks, such as answering "Who won the latest World Cup?" because the knowledge they learn during training may be insufficient or outdated. Conditioning generation on…
Despite the widespread use of statistical prior models in various fields, such models for neural network gradients have long been overlooked. The inherent challenge stems from their high-dimensional structures and complex interdependencies,…