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

ContractNLI

Benchmarks

Task NameDataset NameSOTA ResultTrend
Legal Contract RevisionContractNLI
CQ87.03
25
Natural Language InferenceContractNLI re-annotated (test)
Accuracy83
20
Legal TaskContractNLI
Performance79.9
18
Natural Language InferenceContractNLI
Macro-F184.5
8
Contract UnderstandingContractNLI
Expected Calibration Error (ECE)4.04
6
Explanation GenerationContractNLI
NLI Score57.8
5
Text ClassificationContractNLI
mF184.9
5
Natural Language InferenceContractNLI SCROLLS (test)
Exact Match (EM)59.38
3
Showing 8 of 8 rows