Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention
Open paper
Benchmark
Model
Rank
Results
question-answering-on-hotpotqa
Transformer-XH-final
#12
JOINT-F1: 0.513
ANS-EM: 0.516
ANS-F1: 0.641
SUP-EM: 0.409
…
Rank counts only results with a code link.