Fusing Context Into Knowledge Graph for Commonsense Question Answering

Open paper
Benchmark Model Rank Results
common-sense-reasoning-on-commonsenseqaDEKCOR#5Accuracy: 83.3
question-answering-on-openbookqaTTTTT 3B#5Accuracy: 83.2
question-answering-on-openbookqaDEKCOR#9Accuracy: 82.4

Rank counts only results with a code link.