基于 LLM 的模型无关 PII 检测

原标题：Model-agnostic PII detection with LLMs

AWS Machine Learning Blog一手来源教程质量 71

AI 摘要

AWS Machine Learning Blog 介绍了一种基于 LLM 的模型无关 PII 检测器，通过指令驱动检测逻辑，可在 Amazon Bedrock 或自托管模型上运行。该方案将实体类型和输出格式变为可配置项，无需重新训练即可扩展检测范围，并在五个公开 PII 语料库上与包括 OpenAI PrivacyFilter 在内的九种 LLM 检测器进行了对比评估。

以上摘要由 AI 生成，可能存在误差。事实请以原文为准。

正文节选

Model-agnostic PII detection with LLMs A configurable, instruction-driven detector that runs on any large language model (LLM) managed on Amazon Bedrock, evaluated on five public PII corpora across nine LLM-based detectors, including the OpenAI PrivacyFilter. Fine-tuning a model on real-world text creates a personally identifiable information (PII) detection problem. Training corpora are full of PII: names, home addresses, email and phone numbers, national-ID and social-security numbers, bank ac

发布时间：2026-09-11 00:02

抓取时间：2026-09-11 00:17

来源机构：AWS

阅读原文aws.amazon.com