链式净化思维：在大推理模型的CoT中消除PII泄露
Chain-of-Sanitized-Thoughts: Plugging PII Leakage in CoT of Large Reasoning Models
AI总结：
本文提出PII-CoT-Bench，通过部署干预措施减少大推理模型中链式思维推理的PII泄露，证明隐私优先推理可在不牺牲性能的情况下实现。
摘要：
大推理模型（LRMs）通过生成显式的链式思维（CoT）推理来提高性能、可靠性和可解释性，但这种透明性引入了严重的隐私风险：即使最终答案被净化，中间推理过程往往仍会泄露个人身份信息（PII）。我们研究如何诱导以隐私为优先的推理，使模型在不暴露敏感信息的情况下进行推理，采用可部署的干预措施而非事后修正。我们引入PII-CoT-Bench，一个带有隐私意识的CoT标注监督数据集，以及一个涵盖现实和对抗性泄露场景的类别平衡评估基准。我们的结果揭示了一种能力依赖的趋势：最先进的模型最受益于基于提示的控制，而较弱的模型需要微调才能实现有意义的泄露减少。在模型和类别层面，两种方法均显著减少了PII暴露，同时对效用的损害极小，证明了在不牺牲性能的情况下可以实现隐私推理。总体而言，我们展示了在最小效用损失的情况下可以实现隐私CoT推理，为构建隐私保护的推理系统提供了实用指导。
英文摘要：
Large Reasoning Models (LRMs) improve performance, reliability, and interpretability by generating explicit chain-of-thought (CoT) reasoning, but this transparency introduces a serious privacy risk: intermediate reasoning often leaks personally identifiable information (PII) even when final answers are sanitized. We study how to induce privacy-first reasoning, where models reason without exposing sensitive information, using deployable interventions rather than post-hoc redaction. We introduce PII-CoT-Bench, a supervised dataset with privacy-aware CoT annotations, and a category-balanced evaluation benchmark covering realistic and adversarial leakage scenarios. Our results reveal a capability-dependent trend: state-of-the-art models benefit most from prompt-based controls, whereas weaker models require fine-tuning to achieve meaningful leakage reduction. Across models and categories, both approaches substantially reduce PII exposure with minimal degradation in utility, demonstrating that private reasoning can be achieved without sacrificing performance. Overall, we show that private CoT reasoning can be achieved with minimal utility loss, providing practical guidance for building privacy-preserving reasoning systems.
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。
