Large Language Models (LLMs) and Generative Pre-trained Transformers (GPTs) for Legal

A list of selected and curated information dedicated to Legal LLMs and GPTs.

Photo by Brett Jordan on Unsplash

Please read the contribution guidelines before contributing. Please add a resource by raising a pull request. We also seek for discussion and proposal of new ideas (including additional content sections) as issues.

Contents

• Large Language Models and GPT for Legal
• Tutorials
• Prompt Engineering
• ChatGPT Detection
• Foundations of Legal Text Analytics
• Selected Articles on Technological Aspects
• Selected Articles on Legal and Regulatory Aspects
• Credits

Large Language Models and GPTs for Legal

Back to Top

• Stephen Wolfram: What Is ChatGPT Doing … and Why Does It Work?
• Transformer models: an introduction and catalog
• ChatGPT at OpenAI
  • Examples
  • Documentation
  • Pricing
  • Fine-tuning ChatGPT
  • Sketch summarizing ChatGPT
• OpenAI Evaluation Toolkit
• LLaMA: Open and Efficient Foundation Language Models
• Large Language Models: Report by KI Bundesverband
• Large Language Models: Hugging Face Report
• GPT Takes the Bar Exam
• Large Language Models as Corporate Lobbyists
• Legal Prompt Engineering for Multilingual Legal Judgement Prediction
• Towards Reasoning in Large Language Models: A Survey
• Report on Limitations of ChatGPT

Tutorials

Back to Top

• OpenAI Cookbook shares example code for accomplishing common tasks with the OpenAI API
• GPT in 60 Lines of NumPy
• Beginner’s Guide to the GPT-3 Model
• Using ChatGPT in Python
• Mastering the GPT-3 API in Python
• ChatGPT CLI and Python Wrapper
• Building GPT-3 applications — beyond the prompt
• Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Prompt Engineering

Back to Top

• Training language models to follow instructions with human feedback
• Prompt Engineering Guide
• Awesome ChatGPT Prompts
• Best practices for prompt engineering with OpenAI API
• Prompt Engineering 101 - Introduction and resources
• So you want to be a prompt engineer: Critical careers of the future
• Free Dolly: Introducing the World's First Truly Open Instruction-Tuned LLM
• More than 15k prompts: open source dataset of instruction-following records

ChatGPT Detection

Back to Top

• How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection
• ChatGPT-Comparison-Detection Project

Selected Articles on Technological Aspects

Back to Top

• On the Explainability of Natural Language Processing Deep Models
• Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey
• Language models are few-shot learners: Train GPT-3 - an autoregressive language model with 175 billion parameters
  • Supplemental Material
• Language Models are Changing AI. We Need to Understand Them
• ChatGPT Is a Blurry JPEG of the Web

Selected Articles on Legal and Regulatory Aspects

Back to Top

• Auditing Large Language Models: A Three-Layered Approach
• Regulating ChatGPT and other Large Generative AI Models
• Law, Policy, & AI Update: China Requires AI Watermarks, ChatGPT Won’t Make it to U.S. Courtrooms

Foundations of Legal Text Analytics

Back to Top

• See Methods for Legal Text Analytics
• See Libraries for Legal Text Analytics
• See Datasets and Data for Legal Text Analytics
• See Tutorials for Legal Text Analytics
• See Research Groups, Labs, and Communities for Legal Text Analytics

Credits

Back to Top

See contributors and committers (and many more).

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.