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

CovidQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question AnsweringCovidQA
F147.64
17
Question AnsweringCovidQA
Accuracy67.59
15
Machine-generated text detectionCovidQA Community ChatGPT-generated (test)
AUROC0.9923
11
Hallucination DetectionCovidQA
F1 Score91.7
6
Retrieval-Augmented GenerationCovidQA
Faithfulness79.7
5
Showing 5 of 5 rows