法律界可用AI处理敏感信息而不泄密。
LegalGuardian: A Privacy-Preserving Framework for Secure Integration of Large Language Models in Legal Practice
- 用本地小模型识别并遮蔽敏感信息
- 遮蔽后仍保持97%信息准确率
- 适合需要保护隐私的律师使用
大型语言模型（LLMs）有望通过自动化复杂任务和提升司法可及性来推动法律实践发展。然而，律师在提示中包含敏感个人身份信息（PII）时，会引发客户保密性担忧，存在数据泄露风险。为此，我们提出LegalGuardian——一种专为律师设计的轻量级隐私保护框架。该框架结合命名实体识别（NER）与本地LLM，对提示中的敏感信息进行遮蔽与还原，确保在外部交互前数据安全。我们在移民法场景下使用合成提示库评估其效果，对比传统NER模型与单次提示的本地LLM，发现LegalGuardian在PII检测上分别达到93%（GLiNER）和97%（Qwen2.5-14B）的F1得分。语义相似性分析表明，输出内容保持高保真度，有效保障了LLM工具的实用性。结果表明，法律从业者可在不牺牲客户隐私或文书质量的前提下，安全使用先进AI技术。
原文摘要 · Abstract (English)
Large Language Models (LLMs) hold promise for advancing legal practice by automating complex tasks and improving access to justice. However, their adoption is limited by concerns over client confidentiality, especially when lawyers include sensitive Personally Identifiable Information (PII) in prompts, risking unauthorized data exposure. To mitigate this, we introduce LegalGuardian, a lightweight, privacy-preserving framework tailored for lawyers using LLM-based tools. LegalGuardian employs Named Entity Recognition (NER) techniques and local LLMs to mask and unmask confidential PII within prompts, safeguarding sensitive data before any external interaction. We detail its development and assess its effectiveness using a synthetic prompt library in immigration law scenarios. Comparing traditional NER models with one-shot prompted local LLM, we find that LegalGuardian achieves a F1-score of 93% with GLiNER and 97% with Qwen2.5-14B in PII detection. Semantic similarity analysis confirms that the framework maintains high fidelity in outputs, ensuring robust utility of LLM-based tools. Our findings indicate that legal professionals can harness advanced AI technologies without compromising client confidentiality or the quality of legal documents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。