发表机构
Mphasis Limited（美费西斯有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出一种基于指令微调语言模型的领域无关可解释文本脱敏方案，支持用户以自然语言定义敏感信息，可应用于法律、医疗等关键场景的自动文本脱敏。
AI 中文摘要
随着个人与企业通信数字化程度不断提升，文本数据的自动脱敏已成为数据隐私与合规框架的关键组成部分。传统文本脱敏方案主要适用于对个人身份信息（PII）等具有标准结构的敏感数据进行模糊处理，且无法为其脱敏操作提供透明的依据，导致难以对其进行审计。本文提出一种可解释的领域无关文本脱敏方案，该方案利用自然语言脱敏规则，通过指令微调的语言模型对非结构化文档中的敏感信息进行识别与脱敏。与传统文本脱敏不同，该方法允许用户以自然语言便捷定义任意敏感信息，包括结构化的（如PII）或非结构化的（如法律条款与条件）内容。通用大语言模型（LLM）会根据用户定义生成或扩充这些自然语言脱敏规则，随后利用这些规则对较小的语言模型进行指令微调，该微调后的模型可针对任意给定文档逐步推理规则，识别并脱敏对应的敏感内容，同时为每一次脱敏操作提供透明的依据，并高亮触发该决策的具体规则。该依据以自然语言生成，用于支持人工审核人员与审计人员理解特定内容被脱敏的原因。研究采用基于重构的指标来估计从脱敏文档中恢复被脱敏信息的概率，以量化脱敏覆盖范围。该方案表现出较高的重构误差与较高的脱敏精度，适用于法律开示、医疗文档、企业信息治理等关键应用场景中的自动文本脱敏。
英文摘要
With the increasing digitization of personal and corporate communication, the automatic sanitization of textual data has become a crucial component of data privacy and compliance frameworks. Traditional text sanitization solutions are majorly suitable for obscuring sensitive data with standard structure such as Personal Identifiable Information (PII). These solutions do not provide transparent justification for their redaction, which makes it difficult to audit them. This paper introduces an explainable, domain-agnostic text redaction solution that uses natural language rules of redaction, applied via an instruction-tuned language model, to identify and redact sensitive information in unstructured documents. Unlike traditional text sanitization, this method enables a user to conveniently define any sensitive information; which may be structured (e.g.\ PII) or unstructured (e.g.\ legal terms and conditions) in natural language. A general-purpose LLM generates or augments these natural language rules of redaction from the user's definition, which are then used to instruction-fine-tune a smaller language model that reasons the rules step-by-step over any given document to identify and redact the corresponding sensitive content, while providing transparent justifications for each redaction and highlighting the specific rule that triggered the decision. This explanation is generated in natural language to support human reviewers and auditors in understanding why specific content was redacted. A reconstruction-based metric is used to estimate the probability of recovering redacted information from the sanitized document, quantifying redaction coverage. The solution shows high reconstruction error and high redaction precision, making it suitable for automated text sanitization in critical applications such as legal discovery, medical documentation, and corporate information governance.
