Chinese Legal Statutes Structured for RAG Systems, Current as of 2025

Kuugo's Chinese Law dataset is a collection of current Chinese legal statutes structured for retrieval-augmented generation (RAG) systems. The data is formatted with each legal clause on a separate line and is current as of January 1, 2025. It was last updated on the Hugging Face platform on April 24, 2025.

Use Cases

• Building legal Q&A chatbots based on the structured clause-per-line format.
• Fine-tuning language models for Chinese legal text understanding based on the corpus of statutes.
• Creating a vector database for semantic search of Chinese legal provisions.
• Developing educational tools for studying Chinese law using the organized text data.

Strengths

• Data is explicitly structured with one legal clause per line, which is noted as optimal for vector database chunking.
• The dataset is described as being specifically optimized for RAG system applications.
• A clear temporal cutoff date of January 1, 2025, is provided for the legal content.

Limitations

• The exact number of rows, columns, and total size of the dataset is unknown.
• Column-level documentation is absent; field semantics must be inferred after download.
• License information is not provided, which may restrict usage.

Provenance

Source

Kuugo on Hugging Face

Time Range

Current as of 2025-01-01

Freshness

Last updated 2025-04-24 07:07:29; freshness should be verified

Geography

China