Safer Reasoning Traces: Measuring and Mitigating Chain-of-Thought Leakage in LLMs
arXiv:2603.05618v1 Announce Type: new Abstract: Chain-of-Thought (CoT) prompting improves LLM reasoning but can increase privacy risk by resurfacing personally identifiable information (PII) from the prompt …
Patrick Ahrend, Tobias Eder, Xiyang Yang, Zhiyi Pan, Georg Groh
조회수 48회