CAPID: 基于上下文的PII检测用于问答系统
CAPID: Context-Aware PII Detection for Question-Answering Systems
AI总结：
CAPID通过微调本地小型语言模型实现隐私保护的PII检测，有效提升问答系统中PII识别的准确性与实用性。
摘要：
在用户查询中检测个人可识别信息（PII）对于确保问答系统中的隐私至关重要。当前方法主要擦除所有PII，忽视了其中一些可能与用户问题上下文相关的情况，导致响应质量下降。大型语言模型（LLMs）可能有助于确定哪些PII相关，但因其封闭源代码和缺乏隐私保障，不适合处理敏感数据。为了实现隐私保护的PII检测，我们提出CAPID，一种实用的方法，通过微调本地拥有的小型语言模型（SLM）在传递到LLMs进行问答之前过滤敏感信息。然而，现有数据集未能捕捉到需要训练此类模型的有效性所需的上下文依赖性PII相关性。为填补这一空白，我们提出了一种合成数据生成管道，利用LLMs生成覆盖多种PII类型和相关性级别的多样化、领域丰富的数据集。使用此数据集，我们微调SLM以检测PII跨度、分类其类型并估计上下文相关性。我们的实验表明，使用微调SLM的上下文感知PII检测在跨度、相关性和类型准确性方面显著优于现有基线，同时在匿名化下保持更高的下游效用。
英文摘要：
Detecting personally identifiable information (PII) in user queries is critical for ensuring privacy in question-answering systems. Current approaches mainly redact all PII, disregarding the fact that some of them may be contextually relevant to the user's question, resulting in a degradation of response quality. Large language models (LLMs) might be able to help determine which PII are relevant, but due to their closed source nature and lack of privacy guarantees, they are unsuitable for sensitive data processing. To achieve privacy-preserving PII detection, we propose CAPID, a practical approach that fine-tunes a locally owned small language model (SLM) that filters sensitive information before it is passed to LLMs for QA. However, existing datasets do not capture the context-dependent relevance of PII needed to train such a model effectively. To fill this gap, we propose a synthetic data generation pipeline that leverages LLMs to produce a diverse, domain-rich dataset spanning multiple PII types and relevance levels. Using this dataset, we fine-tune an SLM to detect PII spans, classify their types, and estimate contextual relevance. Our experiments show that relevance-aware PII detection with a fine-tuned SLM substantially outperforms existing baselines in span, relevance and type accuracy while preserving significantly higher downstream utility under anonymization.
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。
