CHiSafetyBench：面向大语言模型的中文层级安全基准
CHiSafetyBench: A Chinese Hierarchical Safety Benchmark for Large Language Models
AI总结：
本文提出中文层级安全基准CHiSafetyBench，覆盖5大风险领域和31个类别，通过多选题与问答任务评估大语言模型识别风险内容及拒绝回答风险问题的能力，并验证了自动评估的可行性。
摘要：
随着大语言模型（LLMs）的深入发展，其安全问题日益受到关注。然而，目前针对大语言模型的中文安全基准十分稀缺，且现有的安全分类体系不够完善，缺乏在真实中文场景下全面的安全检测能力。本文提出了CHiSafetyBench，这是一个专门用于评估大语言模型在中文语境下识别风险内容以及拒绝回答风险问题能力的安全基准。CHiSafetyBench包含一个数据集，覆盖了由5个风险领域和31个类别构成的中文层级安全分类体系。该数据集包含两类任务：多项选择题和问答，分别从风险内容识别能力和拒绝回答风险问题的能力两个角度评估大语言模型。利用该基准，我们验证了自动评估替代人工评估的可行性，并对主流中文大语言模型进行了全面的自动安全评估。实验结果显示，不同模型在不同安全领域上的表现存在差异，表明所有模型在中文安全能力方面仍有较大的提升空间。我们的数据集已在 https://github.com/UnicomAI/UnicomBenchmark/tree/main/CHiSafetyBench 公开。
英文摘要：
With the profound development of large language models(LLMs), their safety concerns have garnered increasing attention. However, there is a scarcity of Chinese safety benchmarks for LLMs, and the existing safety taxonomies are inadequate, lacking comprehensive safety detection capabilities in authentic Chinese scenarios. In this work, we introduce CHiSafetyBench, a dedicated safety benchmark for evaluating LLMs' capabilities in identifying risky content and refusing answering risky questions in Chinese contexts. CHiSafetyBench incorporates a dataset that covers a hierarchical Chinese safety taxonomy consisting of 5 risk areas and 31 categories. This dataset comprises two types of tasks: multiple-choice questions and question-answering, evaluating LLMs from the perspectives of risk content identification and the ability to refuse answering risky questions respectively. Utilizing this benchmark, we validate the feasibility of automatic evaluation as a substitute for human evaluation and conduct comprehensive automatic safety assessments on mainstream Chinese LLMs. Our experiments reveal the varying performance of different models across various safety domains, indicating that all models possess considerable potential for improvement in Chinese safety capabilities. Our dataset is publicly available at https://github.com/UnicomAI/UnicomBenchmark/tree/main/CHiSafetyBench.
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。
