DEKCOR

Reported on 2 benchmarks across 2 tasks · 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 Processing2 results

Common Sense ReasoningonCommonsenseQA
Accuracy· uses extra data· 2020-12-09
83.3
best: 92.54 (GPT-4o (HPT))
SOTA
Fusing Context Into Knowledge Graph for Commonsense Question Answering arXiv:2012.04808
Question AnsweringonOpenBookQA
Accuracy· 2020-12-09
82.4
best: 95.9 (GPT-4 + knowledge base)
Fusing Context Into Knowledge Graph for Commonsense Question Answering arXiv:2012.04808