Answering Open-Domain Questions of Varying Reasoning Steps from Text

Open paper
Benchmark Model Rank Results
question-answering-on-hotpotqaIRRR+#5JOINT-F1: 0.696ANS-EM: 0.663ANS-F1: 0.791SUP-EM: 0.569…
question-answering-on-hotpotqaIRRR#6JOINT-F1: 0.686ANS-EM: 0.657ANS-F1: 0.782SUP-EM: 0.559…

Rank counts only results with a code link.