Citation F1
A text-matching evaluation metric that computes the harmonic mean of precision and recall between the statutes a model cites and the statutes actually cited in court judgments. It attends only to matching statute numbers and is insensitive to changes in statutory content.
Timeline (last 90 days)
NitiBench+'s evaluation system combines the Thai Bar Association scoring standard, the Bar standard score, and the overlap between cited legal provisions and the provisions actually cited by the court (Citation F1).
The Citation F1 metric completely fails to capture the differences in errors caused by legal temporal validity.
All Facts (2)
NitiBench+'s evaluation system combines the Thai Bar Association scoring standard, the Bar standard score, and the overlap between cited legal provisions and the provisions actually cited by the court (Citation F1).
50%UnverifiedThe Citation F1 metric completely fails to capture the differences in errors caused by legal temporal validity.
50%