⚫ A spaCy pipeline and model for NLP on unstructured legal text.

Benchmarking Legal Knowledge of Large Language Models

all kinds of baseline models for long text classificaiton( text categorization)

USA Federal Individual Income and Payroll Tax Microsimulation Model

对收集的法律文档进行一系列分析，包括根据规范自动切分、案件相似度计算、案件聚类、法律条文推荐等（试验目前基于婚姻类案件，可扩展至其它领域）。

爬取北大法宝网http://www.pkulaw.cn/Case/

Anonymous, end-to-end encrypted reporting for organizations and individuals.

The code used to create and update the Open Australian Legal Corpus, the first and only multijurisdictional open corpus of Australian legislative and judicial documents.

中国法研杯-司法人工智能挑战赛

US Bill Summarization Corpus

A corporate law RAG system with innovative retrieval and contextual strategies

中国常用法律查询手册 | Law-Book

Chatbot for Indian Law using Llama-7B-chat using Langchain integration and Streamlit UI.

Backend for columnar, fully orchestrated HEP analyses with pure Python, law and order.

A curated collection of Agent Skills for legal work.

The code used to evaluate embedding models on the Massive Legal Embedding Benchmark (MLEB).

A PoC for a location-aware legal assistant powered by GPT-4 and Gradio.

UK legal API for AI agents and researchers.

A Backend for a Lawyer Appointement System

AI-powered legal analysis to simplify compliance. This tool transforms complex documents into plain English, assesses risks, and checks against regulations like GDPR & PDPA. An IBM TechXchange Hackathon 2025 project built with FastAPI, React, and IBM WatsonX.