DISC-LawLLM

Visit Tool

DISC-LawLLM is an open-source Chinese legal large language model (LLM) that provides a wide range of legal services. It offers legal text processing, reasoning, and knowledge retrieval capabilities.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is DISC-LawLLM?

DISC-LawLLM is an intelligent legal system powered by large language models (LLMs), developed and open-sourced by Fudan University's Data Intelligence and Social Computing Laboratory (Fudan-DISC). It offers comprehensive legal services, including legal text processing for information extraction and summarization, and legal reasoning capabilities enhanced by legal syllogism theory. The system also features a retrieval-augmented module for improved knowledge adherence, utilizing a vast knowledge base of laws and legal exam questions. DISC-LawLLM provides high-quality training datasets, effective training paradigms, and a robust evaluation framework, with its performance on the Lawbench benchmark ranking second only to GPT-4 among legal LLMs.

Best used for

Ideal for legal professionals and researchers who need to analyze legal texts, perform complex legal reasoning, and retrieve specific legal information. Especially valuable for tasks like legal consultation, drafting agreements, and preparing for legal examinations within the Chinese legal context.

Common actions

process legal documents

perform legal reasoning

retrieve legal information

draft legal agreements

assist with legal exams

face swappinggithub copilotdeepfakeopen-source"AI Agents"collaborationlow-code/no-codeautomated workflowworkflows

Capabilities

Key features

Legal text processing
Legal reasoning
Knowledge retrieval
Legal consultation
Agreement drafting
Judicial tools

Target Audience

lawyerprofessor

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What kind of legal services does DISC-LawLLM provide?

DISC-LawLLM offers a wide range of intelligent legal services, including legal text processing (information extraction, summarization), legal reasoning, knowledge retrieval, legal consultation, agreement drafting, and assistance with judicial professional tools and legal exams.

What datasets are available with DISC-LawLLM?

DISC-LawLLM provides the DISC-Law-SFT dataset, which includes sub-datasets for legal information extraction, judgment prediction, document summarization, and legal Q&A. It also includes the DISC-Law-Eval Benchmark for evaluating legal large language models.

How does DISC-LawLLM enhance its knowledge retrieval capabilities?

DISC-LawLLM integrates a retrieval-augmented module based on Langchain-Chatchat. Its knowledge base includes over 800 national and local laws and regulations, as well as 24,000 legal examination questions, enhancing its ability to retrieve and adhere to background knowledge.

Trending

Subcategories trending in Productivity & Business

Workflow Automation Strategy & Planning HR & Recruiting Document Management Team Collaboration Startup Tools

Trending

Also listed in

This tool also appears in

Research & Education › Academic Research Coding & Development › Open Source & Models

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce