S-Eval：面向大语言模型的自动化全面安全评估
S-Eval: Towards Automated and Comprehensive Safety Evaluation for Large Language Models
AI总结：
针对大语言模型安全评估缺乏统一风险分类体系与自动化技术的问题，提出含双LLM组件的S-Eval自动化评估框架，可高效生成测试用例并输出可解释量化评估结果，已在工业场景验证有效性。
摘要：
生成式大语言模型（LLM）凭借其变革性与涌现能力，为自然语言处理领域带来了革命性变化。但近期研究表明，大语言模型可能生成违反社会规范的有害内容，这使得部署这类先进模型的安全性与伦理影响引发了广泛担忧。因此，在部署前对大语言模型开展严格、全面的安全评估至关重要且迫在眉睫。尽管存在这一需求，但由于大语言模型生成空间极为广阔，目前仍缺乏能系统反映大语言模型内容安全状况的统一标准化风险分类体系，也缺少可高效挖掘潜在风险的自动化安全评估技术。\n为填补这一显著空白，我们提出了S-Eval——一种基于大语言模型的新型自动化安全评估框架，该框架配套了一套全新定义的综合风险分类体系。S-Eval包含两个核心组件，分别是专家测试大语言模型$M_t$和新型安全评判大语言模型$M_c$。其中，$M_t$负责依据所提出的风险分类体系自动生成测试用例；$M_c$则可提供量化且可解释的安全评估结果，帮助更好地感知大语言模型的风险。与已有研究相比，S-Eval在测试生成和安全评估两方面均兼具高效性与有效性。此外，得益于基于大语言模型的架构，S-Eval可灵活配置，能够适配大语言模型的快速迭代，以及随之出现的新型安全威胁、测试生成方法和安全评判方法。目前S-Eval已在我们的产业合作伙伴处部署，用于为服务数百万用户的多款大语言模型开展自动化安全评估，验证了其在真实场景下的有效性。我们的基准测试集已公开于https://github.com/IS2Lab/S-Eval。
英文摘要：
Generative large language models (LLMs) have revolutionized natural language processing with their transformative and emergent capabilities. However, recent evidence indicates that LLMs can produce harmful content that violates social norms, raising significant concerns regarding the safety and ethical ramifications of deploying these advanced models. Thus, it is both critical and imperative to perform a rigorous and comprehensive safety evaluation of LLMs before deployment. Despite this need, owing to the extensiveness of LLM generation space, it still lacks a unified and standardized risk taxonomy to systematically reflect the LLM content safety, as well as automated safety assessment techniques to explore the potential risk efficiently. To bridge the striking gap, we propose S-Eval, a novel LLM-based automated Safety Evaluation framework with a newly defined comprehensive risk taxonomy. S-Eval incorporates two key components, i.e., an expert testing LLM ${M}_t$ and a novel safety critique LLM ${M}_c$. ${M}_t$ is responsible for automatically generating test cases in accordance with the proposed risk taxonomy. ${M}_c$ can provide quantitative and explainable safety evaluations for better risk awareness of LLMs. In contrast to prior works, S-Eval is efficient and effective in test generation and safety evaluation. Moreover, S-Eval can be flexibly configured and adapted to the rapid evolution of LLMs and accompanying new safety threats, test generation methods and safety critique methods thanks to the LLM-based architecture. S-Eval has been deployed in our industrial partner for the automated safety evaluation of multiple LLMs serving millions of users, demonstrating its effectiveness in real-world scenarios. Our benchmark is publicly available at https://github.com/IS2Lab/S-Eval.
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。
