NYU defines an interestingness metric for theorems and trains a 27B model to discover new math

nyuniversity · hf · 2026-09-26

NYU researchers propose quantifying a theorem's intrinsic interestingness as the ratio of proof length to statement length, showing it strongly correlates with downstream utility.

Related event: NYU Defines "Interestingness" Metric for LLMs to Discover Math(3 posts)→

Original post →

More from Research

Research channel →