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

Restaurants

Benchmarks

Task NameDataset NameSOTA ResultTrend
Aspect Robustness TestRestaurants14 ARTS (test)
Accuracy81.55
6
Named Entity RecognitionRestaurants
F1 Score52.7
5
Pairwise LLM EvaluationRestaurants
Win Rate (Contrast)83
2
Query-driven contrastive summarizationRestaurants (test)
Contrast Win Rate87
2
Contrastive SummarizationRestaurants
Contrast87
2
Showing 5 of 5 rows