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

SituatedQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Binary ill-posedness detectionSituatedQA
Accuracy90.4
18
Document Retrieval (Implicit Temporal Information)SituatedQA 2021
nDCG@539.4
12
Document Retrieval (Implicit Temporal Information)SituatedQA 2020
nDCG@535.91
12
Document Retrieval (Implicit Temporal Information)SituatedQA 2019
nDCG@534.36
12
Document Retrieval (Implicit Temporal Information)SituatedQA 2018
nDCG@50.4411
12
Document Retrieval (Explicit Temporal Information)SituatedQA 2021
nDCG@540.21
12
Document Retrieval (Explicit Temporal Information)SituatedQA 2020
nDCG@536.31
12
Document Retrieval (Explicit Temporal Information)SituatedQA 2019
nDCG@532.87
12
Document Retrieval (Explicit Temporal Information)SituatedQA 2018
nDCG@543.93
12
Information RetrievalSituatedQA 2021
nDCG@540.21
7
Information RetrievalSituatedQA 2018
nDCG@50.4411
7
Open-Domain QASituatedQA Nq=300
Accuracy44.6
6
Showing 12 of 12 rows