
Evaluation as a Product: Aron Ahmadia on Benchmarking TAR vs. LLMs for Legal Review
Ahead of RelFest in Chicago, Relativity’s VP of Applied Science, Aron Ahmadia, joins the podcast to talk AI evaluation: what “evaluation as a product” means, why private benchmarks matter, and how testing LLMs differs from testing traditional predictive coding. He also unpacks a recent study pitting TAR and human review against aiR for Review, and shares his take on what’s changing in legal tech next year, and what isn’t.
