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

WOS

Benchmarks

Task NameDataset NameSOTA ResultTrend
Hierarchical Text ClassificationWOS
Macro-F182.29
48
Hierarchical Text ClassificationWOS few-shot
Micro-F182.09
20
Hierarchical Text ClassificationWOS (test)
Micro-F187.71
20
Text classificationWOS-46985 W.3 (test)
Accuracy82.42
12
Text classificationWOS-11967 W.2 (test)
Accuracy91.59
12
Text classificationWOS-5736 W.1 (test)
Accuracy93.57
12
Retrieval-Augmented GenerationWOS
Indexing Time (mins)2
11
Text ClassificationWOS (test)
Hallucinated Rate0.4
10
Hierarchical Text ClassificationWOS full-shot
Micro-F187.1
5
Hierarchical Text ClassificationWOS few-shot bert-large-uncased
Micro-F1-
0
Hierarchical Text ClassificationWOS full-shot bert-base-uncased
Micro-F1-
0
Showing 11 of 11 rows