CValues：从安全到责任衡量中文大语言模型的价值观
CValues: Measuring the Values of Chinese Large Language Models from Safety to Responsibility
AI总结：
本文提出首个中文人类价值观评估基准CValues，从安全与责任维度评估大语言模型对齐能力，通过人工+自动评估发现中文大模型责任维度仍有提升空间。
摘要：
随着大语言模型（LLMs）的快速发展，人们越来越担忧它们可能带来风险或产生负面社会影响，因此人类价值观对齐评估变得愈发重要。以往研究主要聚焦于评估大语言模型在特定知识与推理能力上的表现，却忽视了其与人类价值观的对齐情况，中文语境下的相关研究尤为匮乏。本文提出CValues，这是首个从安全与责任双重标准衡量大语言模型对齐能力的中文人类价值观评估基准。研究中，我们人工收集了覆盖10个场景的对抗性安全提示词，并由专业专家归纳出8个领域的责任类提示词。为实现对中文大语言模型价值观的全面评估，我们既开展人工评估以保障对比的可靠性，还构建了选择题形式的提示词用于自动评估。研究结果显示，多数中文大语言模型在安全维度表现良好，但在责任维度仍有较大提升空间；此外，自动评估与人工评估在不同维度上对衡量人类价值观对齐均具有重要作用。该基准与代码已在ModelScope和Github上开源。
英文摘要：
With the rapid evolution of large language models (LLMs), there is a growing concern that they may pose risks or have negative social impacts. Therefore, evaluation of human values alignment is becoming increasingly important. Previous work mainly focuses on assessing the performance of LLMs on certain knowledge and reasoning abilities, while neglecting the alignment to human values, especially in a Chinese context. In this paper, we present CValues, the first Chinese human values evaluation benchmark to measure the alignment ability of LLMs in terms of both safety and responsibility criteria. As a result, we have manually collected adversarial safety prompts across 10 scenarios and induced responsibility prompts from 8 domains by professional experts. To provide a comprehensive values evaluation of Chinese LLMs, we not only conduct human evaluation for reliable comparison, but also construct multi-choice prompts for automatic evaluation. Our findings suggest that while most Chinese LLMs perform well in terms of safety, there is considerable room for improvement in terms of responsibility. Moreover, both the automatic and human evaluation are important for assessing the human values alignment in different aspects. The benchmark and code is available on ModelScope and Github.
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。
