相关论文: Large Language Models Relearn Removed Concepts

We surely enjoy the larger the better models for their superior performance in the last couple of years when both the hardware and software support the birth of such extremely huge models. The applied fields include text mining and others.…

Model pruning technique is vital for accelerating large language models by reducing their size and computational requirements. However, the generalizability of existing pruning methods across diverse datasets and tasks remains unclear.…

Structured pruning is one of the representative techniques for compressing large language models (LLMs) to reduce GPU memory consumption and accelerate inference speed. It offers significant practical value in improving the efficiency of…

Understanding and shaping the behaviour of Large Language Models (LLMs) is increasingly important as applications become more powerful and more frequently adopted. This paper introduces a machine unlearning method specifically designed for…

Large language models (LLMs) have revolutionized natural language processing, yet their substantial model sizes often require substantial computational resources. To preserve computing resources and accelerate inference speed, it is crucial…

Large language models (LLMs) often develop learned mechanisms specialized to specific datasets, such as reliance on domain-specific correlations, which yield high-confidence predictions without generalizable reasoning. While beneficial in…

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…

Despite the superior performance, it is challenging to deploy foundation models or large language models (LLMs) due to their massive parameters and computations. While pruning is a promising technique to reduce model size and accelerate the…

Recent work has shown that layer pruning can effectively compress large language models (LLMs) while retaining strong performance on classification benchmarks, often with little or no finetuning. In contrast, generative reasoning tasks,…

This work suggests fundamentally rethinking the current practice of pruning large language models (LLMs). The way it is done is by divide and conquer: split the model into submodels, sequentially prune them, and reconstruct predictions of…

Despite the impressive capabilities of generating images, text-to-image diffusion models are susceptible to producing undesirable outputs such as NSFW content and copyrighted artworks. To address this issue, recent studies have focused on…

The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity…

Large language models have been shown to memorize significant portions of their training data, which they can reproduce when appropriately prompted. This work investigates the impact of simple pruning techniques on this behavior. Our…

Pruning-based unlearning has recently emerged as a fast, training-free, and data-independent approach to remove undesired concepts from diffusion models. It promises high efficiency and robustness, offering an attractive alternative to…

Despite exceptional capabilities, Large Language Models (LLMs) still face deployment challenges due to their enormous size. Post-training structured pruning is a promising solution that prunes LLMs without the need for retraining, reducing…

Providing textual concept-based explanations for neurons in deep neural networks (DNNs) is of importance in understanding how a DNN model works. Prior works have associated concepts with neurons based on examples of concepts or a…

Large language models often display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drift, amplification of harmful content, and the propagation of unwanted patterns during extended…

Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data, however, this process might suffer from privacy issues and violations of data protection regulations. As a…

Post-training pruning is an effective approach for reducing the size and inference cost of large language models (LLMs), but existing methods often face a trade-off between pruning quality and computational efficiency. Heuristic pruning…

Generative models such as Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) trained on massive datasets can lead them to memorize and inadvertently reveal sensitive information, raising ethical and privacy concerns.…