相关论文: Exploiting LLM Quantization

While large language models (LLMs) have demonstrated increasing power, they have also given rise to a wide range of harmful behaviors. As representatives, jailbreak attacks can provoke harmful or unethical responses from LLMs, even after…

Large Language Models (LLMs) have shown remarkable capabilities in language understanding and generation. Nonetheless, it was also witnessed that LLMs tend to produce inaccurate responses to specific queries. This deficiency can be traced…

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to…

With the widespread availability of pretrained Large Language Models (LLMs) and their training datasets, concerns about the security risks associated with their usage has increased significantly. One of these security risks is the threat of…

Fine-tuning is a crucial process for adapting large language models (LLMs) to diverse applications. In certain scenarios, such as multi-tenant serving, deploying multiple LLMs becomes necessary to meet complex demands. Recent studies…

Large Language Models (LLMs), which bridge the gap between human language understanding and complex problem-solving, achieve state-of-the-art performance on several NLP tasks, particularly in few-shot and zero-shot settings. Despite the…

Large Language Models (LLMs), characterized by being trained on broad amounts of data in a self-supervised manner, have shown impressive performance across a wide range of tasks. Indeed, their generative abilities have aroused interest on…

Memorization in Large Language Models (LLMs) poses privacy and security risks, as models may unintentionally reproduce sensitive or copyrighted data. Existing analyses focus on average-case scenarios, often neglecting the highly skewed…

Parameter quantization for Large Language Models (LLMs) has attracted increasing attentions recently in reducing memory costs and improving computational efficiency. Early approaches have been widely adopted. However, the existing methods…

The LLaMA family, a collection of foundation language models ranging from 7B to 65B parameters, has become one of the most powerful open-source large language models (LLMs) and the popular LLM backbone of multi-modal large language models…

Quantization is widely adopted to accelerate inference and reduce memory consumption in large language models (LLMs). While activation-weight joint quantization enables efficient low-precision decoding, it suffers from substantial…

We argue that Large language models (LLMs) will soon alter the economics of cyberattacks. Instead of attacking the most commonly used software and monetizing exploits by targeting the lowest common denominator among victims, LLMs enable…

Neural network quantization is becoming an industry standard to efficiently deploy deep learning models on hardware platforms, such as CPU, GPU, TPU, and FPGAs. However, we observe that the conventional quantization approaches are…

This work presents a comprehensive evaluation of how quantization affects model bias, with particular attention to its impact on individual demographic subgroups. We focus on weight and activation quantization strategies and examine their…

Although recent quantized Large Language Models (LLMs), such as BitNet, have paved the way for significant reduction in memory usage during deployment with binary or ternary weights, training these models still demands substantial memory…

This study systematically analyzes the vulnerability of 36 large language models (LLMs) to various prompt injection attacks, a technique that leverages carefully crafted prompts to elicit malicious LLM behavior. Across 144 prompt injection…

Large language models (LLMs) have demonstrated remarkable capabilities in various kinds of tasks, while the billion or even trillion parameters bring storage and efficiency bottlenecks for inference. Quantization, particularly…

Large Language Models (LLMs) have recently demonstrated significant potential in time series forecasting, offering impressive capabilities in handling complex temporal data. However, their robustness and reliability in real-world…

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Recent advances in instruction-following large language models (LLMs) have led to dramatic improvements in a range of NLP tasks. Unfortunately, we find that the same improved capabilities amplify the dual-use risks for malicious purposes of…