# LegalGuardian: A Privacy-Preserving Framework for Secure Integration of Large Language Models in Legal Practice

arXiv: https://arxiv.org/abs/2501.10915 · HTML: https://mlsanity.com/paper/2501.10915/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 34 references that are in the map.
- First posted on arXiv 19 Jan 2025.

## Builds on (most cited first, 10 of 10)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Large Language Models Can Be Strong Differentially Private Learners](https://mlsanity.com/paper/2110.05679/) (2021)
- [GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer](https://mlsanity.com/paper/2311.08526/) (2023)
- [Privacy-preserving Neural Representations of Text](https://mlsanity.com/paper/1808.09408/) (2018)
- [Hide and Seek (HaS): A Lightweight Framework for Prompt Privacy Protection](https://mlsanity.com/paper/2309.03057/) (2023)
- [Privacy Preserving Prompt Engineering: A Survey](https://mlsanity.com/paper/2404.06001/) (2024)
- [Protecting User Privacy in Remote Conversational Systems: A Privacy-Preserving framework based on text sanitization](https://mlsanity.com/paper/2306.08223/) (2023)
- [Large Language Model Prompt Chaining for Long Legal Document Classification](https://mlsanity.com/paper/2308.04138/) (2023)
- [Practical Privacy-Preserving Data Science With Homomorphic Encryption: An Overview](https://mlsanity.com/paper/2011.06820/) (2020)

## Built on by (most cited first, 2 of 2)

- [Can Large Language Models Really Recognize Your Name?](https://mlsanity.com/paper/2505.14549/) (2025)
- [Validate Your Authority: Benchmarking LLMs on Multi-Label Precedent Treatment Classification](https://mlsanity.com/paper/2605.17691/) (2026)

## Abstract (arXiv)

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.