Reproduce “Better Call GPT, Comparing Large Language Models Against Lawyers” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Lauren Martin, Nick Whitehouse, Stephanie Yiu, Lizzie Catterson, Rivindu Perera
The AI Center of Excellence at Onit Inc. empirically compared Large Language Models to human legal professionals for legal contract review, demonstrating that top LLMs achieve comparable accuracy to Junior Lawyers and Legal Process Outsourcers while being orders of magnitude faster and significantly more cost-effective.
Key insights
- Large Language Models can achieve accuracy in determining legal issues comparable to that of human Legal Process Outsourcers and Junior Lawyers.
- LLMs offer a substantial advantage in speed and cost efficiency for legal contract review, significantly outperforming human practitioners.
- While human LPOs currently demonstrate a slight lead in precisely locating issues within contracts, LLMs exhibit strong overall performance across key metrics.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.