CASE-Bench：面向大语言模型的上下文感知安全基准
CASE-Bench: Context-Aware SafEty Benchmark for Large Language Models
AI总结：
本文提出CASE-Bench，通过整合上下文信息评估大语言模型的安全性，揭示上下文对人类判断的显著影响，并发现商业模型在安全情境下的响应与人类判断存在明显偏差。
摘要：
对齐大语言模型（LLMs）与人类价值观对于其安全部署和广泛应用至关重要。当前LLM安全基准往往仅关注个体问题的拒绝，忽略了查询所处的上下文，可能导致在安全情境下产生不期望的拒绝，影响用户体验。为解决这一问题，我们引入了CASE-Bench，一种整合上下文的的安全基准。CASE-Bench根据情境完整性理论为分类查询分配独特的、正式描述的上下文。此外，与以往仅依赖少数标注者多数投票的方法不同，我们招募了足够数量的标注者以确保基于功效分析能够检测实验条件间统计显著差异。使用CASE-Bench对各种开源和商业LLM进行的深入分析揭示了上下文对人类判断的显著影响（p<0.0001从z检验），强调了上下文在安全评估中的必要性。我们还发现人类判断与LLM响应之间存在显著不匹配，特别是在安全情境下的商业模型中。
英文摘要：
Aligning large language models (LLMs) with human values is essential for their safe deployment and widespread adoption. Current LLM safety benchmarks often focus solely on the refusal of individual problematic queries, which overlooks the importance of the context where the query occurs and may cause undesired refusal of queries under safe contexts that diminish user experience. Addressing this gap, we introduce CASE-Bench, a Context-Aware SafEty Benchmark that integrates context into safety assessments of LLMs. CASE-Bench assigns distinct, formally described contexts to categorized queries based on Contextual Integrity theory. Additionally, in contrast to previous studies which mainly rely on majority voting from just a few annotators, we recruited a sufficient number of annotators necessary to ensure the detection of statistically significant differences among the experimental conditions based on power analysis. Our extensive analysis using CASE-Bench on various open-source and commercial LLMs reveals a substantial and significant influence of context on human judgments (p<0.0001 from a z-test), underscoring the necessity of context in safety evaluations. We also identify notable mismatches between human judgments and LLM responses, particularly in commercial models within safe contexts.
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。
