S-Eval

S-Eval is designed to be a new comprehensive, multi-dimensional and open-ended safety evaluation benchmark. So far, S-Eval has 220,000 evaluation prompts in total (and is still in active expansion), including 20,000 base risk prompts (10,000 in Chinese and 10,000 in English) and 200,000 corresponding attack prompts derived from 10 popular adversarial instruction attacks. These test prompts are generated based on a comprehensive and unified risk taxonomy, specifically designed to encompass all crucial dimensions of LLM safety evaluation and meant to accurately reflect the varied safety levels of LLMs across these risk dimensions. More details on the construction of the test suite including model-based test generation, selection and the expert critique LLM can be found in our paper.

S-Eval是一款全新的综合性、多维度且开放式的安全评估基准测试集。截至目前，S-Eval总计包含22万个评估提示词（仍在持续扩充中），其中涵盖2万个基础风险提示词（中文、英文各1万个），以及源自10种主流对抗指令攻击的20万个对应攻击提示词。
上述测试提示词均基于统一全面的风险分类体系生成，专门覆盖大语言模型（Large Language Model，LLM）安全评估的全部核心维度，旨在精准反映大语言模型在各风险维度下的安全性能差异。有关该测试套件的构建细节，包括基于模型的测试生成、筛选流程以及依托大语言模型开展的专家评审环节等更多内容，均可在我们的研究论文中查阅。