Resources

Benchmarks and Evaluations

• Addleshaw Goddard: RAG report: Can Large Language Models be good enough for legal due diligence? 

• AdSoLve: Addressing Socio-technical Limitations of LLMs for Medical and Social Computing

• AI Future Forum: AI Adoption in UK Law Firm: Benchmarking Its Adoption and Anticipating The Future

• Ashurst: Vox PopulAI: Lessons from a global law firm's exploration of generative AI

• CodeX - Stanford Law School: A Supervisory AI Agent Approach to Responsible Use of GenAI in the Legal Profession

• Harvey: BigLaw Bench 

• Legal Benchmarks: AI Benchmarks for the Legal Industry 

• Linklaters: The LinksAI English law benchmark / v2 Linklaters Put AI Through Law Exams - Above the Law

• ODI (Open Data Institute): Building a better future with data and AI white paper

• Open Compass LawBench (China): An Evaluation Benchmark Assessing comprehensive performance of Large Language Models (LLM’s) in highly specialized legal domains 

• Oxethica: AI Audit Tool

• Ryan McDonald: Building Your Own Legal Benchmarks for LLMs and Vendor AI Tools

• Stanford LegalBench A collaboratively built large language model benchmark for legal reasoning

• Stanford study: Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools

• UK Government Guidance: Introduction to AI assurance 

• Vals: Legal AI Report

Due Diligence of AI Tools

• Litig AI Due Diligence Questionnaire

Regulation

• UK Government Whitepaper: A pro-innovation approach to AI regulation