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

AlphaNLI

Benchmarks

Task NameDataset NameSOTA ResultTrend
Abductive Natural Language InferenceAlphaNLI n=300 per condition (test)
Accuracy95
21
Multi-agent debateAlphaNLI
Accuracy93.7
15
Showing 2 of 2 rows