Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

NealSmith

Benchmarks

Task NameDataset NameSOTA ResultTrend
Detection of quotation errorsNealSmith Full
SUP F180.08
5
Scientific Claim VerificationNealSmith abstract-level (test)
SUP F1 Score69.03
2
Showing 2 of 2 rows