arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.18369cs.CYcs.CL
收藏

生成式AI大语言模型中的AI安全:一项综述

AI Safety in Generative AI Large Language Models: A Survey

CSIRO’s Data61(联邦科学与工业研究组织Data61);University of New South Wales(新南威尔士大学)

Jaymari Chua, Yun Li, Shiyi Yang, Chen Wang, Lina Yao

AI总结:

本文从计算机科学视角综述了生成式大语言模型的AI安全研究,探讨了LLM风险背景、模型约束、对齐方法及未来方向,旨在为解决AI安全问题提供见解。

摘要:

表现出生成式AI能力的大型语言模型(LLMs),如ChatGPT,正面临加速的采用和创新。生成式AI(GAI)的日益普及不可避免地引发了与这些模型相关的风险和安全担忧。本文从计算机科学家的视角,对GAI-LLMs的AI安全研究近期趋势进行了最新综述:具体且技术性强。在本综述中,我们探讨了在LLMs作为生成式语言模型的背景下已识别危害和风险的背景与动机;我们的综述通过强调在LLMs的研究开发与应用中建立统一理论以应对不同安全挑战的必要性来形成差异化。我们以相关文献为支撑,从对LLMs工作原理的简明介绍开始讨论。随后,我们讨论了早期研究指出的生成模型的根本约束或对其理解的不足(例如,随着LLMs参数数量增加,性能与安全之间的权衡)。我们对LLM对齐提供了充分的覆盖——深入探讨了将LLMs与人类偏好对齐的各种方法、竞争性方法以及当前面临的挑战。通过强调文献中的空白和可能的实施疏漏,我们的目标是创建一项全面的分析,为解决LLMs中的AI安全提供见解,并鼓励开发对齐且安全的模型。最后,我们通过讨论LLMs在AI安全方面的未来方向来总结本综述,为这一关键领域的持续研究提供见解。

英文摘要:

Large Language Model (LLMs) such as ChatGPT that exhibit generative AI capabilities are facing accelerated adoption and innovation. The increased presence of Generative AI (GAI) inevitably raises concerns about the risks and safety associated with these models. This article provides an up-to-date survey of recent trends in AI safety research of GAI-LLMs from a computer scientist's perspective: specific and technical. In this survey, we explore the background and motivation for the identified harms and risks in the context of LLMs being generative language models; our survey differentiates by emphasising the need for unified theories of the distinct safety challenges in the research development and applications of LLMs. We start our discussion with a concise introduction to the workings of LLMs, supported by relevant literature. Then we discuss earlier research that has pointed out the fundamental constraints of generative models, or lack of understanding thereof (e.g., performance and safety trade-offs as LLMs scale in number of parameters). We provide a sufficient coverage of LLM alignment -- delving into various approaches, contending methods and present challenges associated with aligning LLMs with human preferences. By highlighting the gaps in the literature and possible implementation oversights, our aim is to create a comprehensive analysis that provides insights for addressing AI safety in LLMs and encourages the development of aligned and secure models. We conclude our survey by discussing future directions of LLMs for AI safety, offering insights into ongoing research in this critical area.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑