EpiSEM-Bench: Evaluating Safety and Evidence Recovery in LLM Agents under Missing Evidence
Tool-using language model agents rely on environmental facts to decide whether an action is permitted. When a tool response omits a safety-relevant fact, an agent may carry out a prohibited action even though the user request is benign and every returned statement is true. We introduce \bench{}, an executable benchmark for evaluating unsafe execution, safety boundaries, and evidence recovery in LLM agents under missing evidence. It contains 300 matched unsafe/safe task pairs across six domains. By systematically suppressing critical facts, the benchmark measures unsafe execution under critical evidence omission and determines the minimum observed failure cardinality, including failures with full evidence and cases with no observed failure after exhaustive testing. An independent audit tool
评估LLM在关键证据缺失时的安全执行和证据恢复能力的基准测试工具。
- 核心方法
- 引入EpiSEM-Bench，一个包含300对跨六域的不安全/安全任务对的可执行基准，通过系统地抑制关键事实来评估LLM的安全执行边界及证据恢复能力。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 工具使用型语言模型在关键证据缺失时可能执行禁止的操作，即便用户请求是良性的。
- 关键实验
- 包含300对不安全/安全任务，通过抑制关键事实评估模型表现，确定最小观察到的失败基数。
- 主要贡献
- 提供了一种评估LLM在关键证据缺失情况下的安全性和证据恢复能力的方法，有助于提高模型的实际应用安全性。
- 意义与局限
- 为LLM的安全性和可靠性提供了重要评估手段，影响模型开发和应用。但仅限于特定任务，可能无法全面评估所有情况。