Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-hop Question Answering on HotpotQA blind (test)
Loading...
72.69
Answer EM
Beam Retrieval
66.6892
68.2471
69.805
71.3629
Aug 17, 2023
Answer EM
Answer F1
Supporting EM
Supporting F1
Updated 4d ago
Evaluation Results
Method
Method
Links
Answer EM
Answer F1
Supporting EM
Supporting F1
Beam Retrieval
beam size=2
2023.08
72.69
85.04
66.25
90.09
Smoothing R³
2023.08
72.07
84.34
65.44
89.55
FE2H
2023.08
71.89
84.44
64.98
89.14
S2G
2023.08
70.72
83.53
64.3
88.72
HGN
2023.08
69.22
82.19
62.76
88.47
SAE
2023.08
66.92
79.62
61.53
86.86
Feedback
Search any
task
Search any
task