发表机构
OpenAI（OpenAI）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究介绍了OpenAI Privacy Filter模型，这是一款用于检测和编辑非结构化文本中PII及机密的双向令牌分类模型，具备高效部署与可配置特性，可作为数据最小化组件用于隐私工作流。
AI 中文摘要
OpenAI Privacy Filter是一款紧凑的双向令牌分类模型，用于检测和编辑非结构化文本中的个人可识别信息（PII）及机密内容。该模型源自自回归预训练检查点，被转换为双向带注意力分类器，可通过单次前向传播对输入序列进行标注。受限维特比解码器生成涵盖8个隐私类别的连贯跨度，并提供可配置的操作点以权衡精确率与召回率。Privacy Filter总参数为15亿，每令牌激活参数为5000万，上下文窗口达12.8万令牌，设计用于高效本地部署及特定领域微调。其旨在作为分层隐私工作流中可配置的数据最小化组件，而非匿名化或合规性保障。
英文摘要
OpenAI Privacy Filter is a compact, bidirectional token-classification model for detecting and redacting personally identifiable information (PII) and secrets in unstructured text. The model is derived from an autoregressively pretrained checkpoint and converted into a bidirectional, banded-attention classifier that labels an input sequence in a single forward pass. A constrained Viterbi decoder produces coherent spans across eight privacy categories and exposes configurable operating points for precision-recall tradeoffs. Privacy Filter has 1.5 billion total parameters, 50 million active parameters per token, and a 128,000-token context window. It is designed for efficient local deployment and domain-specific fine-tuning. Privacy Filter is intended as a configurable data-minimization component within layered privacy workflows, not as an anonymization or compliance guarantee.
Comments20 pages, 3 figures, 11 tables
