ChineseSafe：评估大型语言模型安全性的中文基准
ChineseSafe: A Chinese Benchmark for Evaluating Safety in Large Language Models
AI总结：
针对现有基准对中文语境下LLMs识别非法和不安全内容能力评估不足的问题，提出符合中国互联网内容审核法规的ChineseSafe基准，涵盖4大类10小类共205,034个示例，评估发现多数LLMs存在安全漏洞，为LLMs内容安全研究提供指导。
摘要：
随着大型语言模型（LLMs）的快速发展，理解LLMs识别不安全内容的能力变得越来越重要。虽然先前的研究已引入多个基准来评估LLMs的安全风险，但学术界对当前LLMs在中文语境下识别非法和不安全内容的能力仍了解有限。在这项工作中，我们提出一个中文安全基准（ChineseSafe），以促进大型语言模型内容安全的研究。为了与中国互联网内容审核法规保持一致，我们的ChineseSafe包含205,034个示例，涵盖4个大类和10个小类的安全问题。针对中文语境，我们增加了几种特殊类型的非法内容：政治敏感、色情以及变体/谐音词。此外，我们采用两种方法评估流行LLMs（包括开源模型和API）的法律风险。结果显示，许多LLMs在某些类型的安全问题上存在漏洞，在中国会导致法律风险。我们的工作为开发者和研究者提供了促进LLMs安全的指导方针。我们的结果还可在https://huggingface.co/spaces/SUSTech/ChineseSafe-Benchmark获取。此外，我们发布了一个包含200,000个示例的测试集，可在https://huggingface.co/datasets/SUSTech/ChineseSafe公开访问。
英文摘要：
With the rapid development of Large language models (LLMs), understanding the capabilities of LLMs in identifying unsafe content has become increasingly important. While previous works have introduced several benchmarks to evaluate the safety risk of LLMs, the community still has a limited understanding of current LLMs' capability to recognize illegal and unsafe content in Chinese contexts. In this work, we present a Chinese safety benchmark (ChineseSafe) to facilitate research on the content safety of large language models. To align with the regulations for Chinese Internet content moderation, our ChineseSafe contains 205,034 examples across 4 classes and 10 sub-classes of safety issues. For Chinese contexts, we add several special types of illegal content: political sensitivity, pornography, and variant/homophonic words. Moreover, we employ two methods to evaluate the legal risks of popular LLMs, including open-sourced models and APIs. The results reveal that many LLMs exhibit vulnerability to certain types of safety issues, leading to legal risks in China. Our work provides a guideline for developers and researchers to facilitate the safety of LLMs. Our results are also available at https://huggingface.co/spaces/SUSTech/ChineseSafe-Benchmark. Additionally, we release a test set comprising 200,000 examples, which is publicly accessible at https://huggingface.co/datasets/SUSTech/ChineseSafe.
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。
