XLNet+GraphReason

Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing1 result

Common Sense ReasoningonCommonsenseQA
Accuracy· 2019-09-09
75.3
best: 92.54 (GPT-4o (HPT))
SOTA
Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering arXiv:1909.05311