CI -Work: Benchmarking Contextual Integrity in Enterprise LLM Agents
Wenjie Fu · Xiaoting Qin · Jue Zhang · Qingwei Lin · Lukas Wutschitz · Robert Sim · Saravan Rajmohan · Dongmei Zhang
摘要
Enterprise LLM agents can dramatically improve workplace productivity, but their core capability, retrieving and using internal context to act on a user’s behalf, also creates new risks for sensitive information leakage. We introduce CI-Work , a Contextual Integrity (CI)-grounded benchmark that s...