Groups legal tasks into memorisation, understanding and application.
Legal AI research
Papers, evidence and connections across jurisdictions.
Uses tax-law problems and synthetic statutes to separate knowledge of legal text from applying rules to facts.
LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
Connects task evaluation to six legally recognisable reasoning categories.
Unifies seven English datasets with accessible evaluation code and comparable metrics.