arXiv 2401.057782024-01-11cs.CLcs.AI

大语言模型系统的风险分类、缓解与评估基准

Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems

Zhongguancun Laboratory（中关村实验室）；Tsinghua University（清华大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Ant Group（蚂蚁集团）

Tianyu Cui, Yanling Wang, Chuanpu Fu, Yong Xiao, Sijia Li, Xinhao Deng, Yunpeng Liu, Qinglin Zhang, Ziyi Qiu, Peiyang Li, Zhixing Tan, Junwu Xiong, Xinyu Kong, … 展开作者

Tianyu Cui, Yanling Wang, Chuanpu Fu, Yong Xiao, Sijia Li, Xinhao Deng, Yunpeng Liu, Qinglin Zhang, Ziyi Qiu, Peiyang Li, Zhixing Tan, Junwu Xiong, Xinyu Kong, Zujie Wen, Ke Xu, Qi Li

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文围绕LLM系统的输入、语言模型、工具链和输出四个模块，提出系统化风险分类与缓解策略，并梳理现有评估基准，以推动负责任的LLM系统建设。

摘要：

大语言模型（LLMs）在解决多种自然语言处理任务方面具有强大能力。然而，LLM系统的安全与保障问题已成为其广泛应用的主要障碍。许多研究已广泛调查了LLM系统中的风险，并制定了相应的缓解策略。OpenAI、Google、Meta和Anthropic等前沿企业也在负责任的LLM方面做出了大量努力。因此，组织现有研究并为社区建立全面分类体系的需求日益增长。本文深入探讨了LLM系统的四个基本模块，包括用于接收提示的输入模块、基于大规模语料训练的语言模型、用于开发和部署的工具链模块，以及用于导出LLM生成内容的输出模块。在此基础上，我们提出了一个全面的分类体系，系统分析了LLM系统各模块相关的潜在风险，并讨论了相应的缓解策略。此外，我们回顾了主流的基准，旨在促进LLM系统的风险评估。我们希望本文能帮助LLM参与者以系统性视角构建负责任的LLM系统。

英文摘要：

Large language models (LLMs) have strong capabilities in solving diverse natural language processing tasks. However, the safety and security issues of LLM systems have become the major obstacle to their widespread application. Many studies have extensively investigated risks in LLM systems and developed the corresponding mitigation strategies. Leading-edge enterprises such as OpenAI, Google, Meta, and Anthropic have also made lots of efforts on responsible LLMs. Therefore, there is a growing need to organize the existing studies and establish comprehensive taxonomies for the community. In this paper, we delve into four essential modules of an LLM system, including an input module for receiving prompts, a language model trained on extensive corpora, a toolchain module for development and deployment, and an output module for exporting LLM-generated content. Based on this, we propose a comprehensive taxonomy, which systematically analyzes potential risks associated with each module of an LLM system and discusses the corresponding mitigation strategies. Furthermore, we review prevalent benchmarks, aiming to facilitate the risk assessment of LLM systems. We hope that this paper can help LLM participants embrace a systematic perspective to build their responsible LLM systems.

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。