Common Sense Reasoning On Commonsenseqa

المقاييس

Accuracy

النتائج

نتائج أداء النماذج المختلفة على هذا المعيار القياسي

جدول المقارنة

اسم النموذج	Accuracy
fusing-context-into-knowledge-graph-for	83.3
unifiedqa-crossing-format-boundaries-with-a	79.1
towards-generalizable-neuro-symbolic-systems	73.2
chain-of-thought-prompting-elicits-reasoning	28.6
kagnet-knowledge-aware-graph-networks-for	58.9
bloomberggpt-a-large-language-model-for	66.4
hierarchical-prompting-taxonomy-a-universal	92.54
unifiedqa-crossing-format-boundaries-with-a	64
unifying-language-learning-paradigms	51.4
star-bootstrapping-reasoning-with-reasoning	68.8
star-bootstrapping-reasoning-with-reasoning	36.6
palm-2-technical-report-1	90.4
unifiedqa-crossing-format-boundaries-with-a	78.1
roberta-a-robustly-optimized-bert-pretraining	72.1
human-parity-on-commonsenseqa-augmenting-self	73.0
bloomberggpt-a-large-language-model-for	64.2
unifying-language-learning-paradigms	34.2
human-parity-on-commonsenseqa-augmenting-self	91.2
deep-bidirectional-language-knowledge-graph	78.2
align-mask-and-select-a-simple-method-for	62.2
muppet-massive-multi-task-representations	79.2
bloomberggpt-a-large-language-model-for	60.4
bloomberggpt-a-large-language-model-for	65.5
star-bootstrapping-reasoning-with-reasoning	72.3
graph-based-reasoning-over-heterogeneous	75.3
explain-yourself-leveraging-language-models	64.7
unifiedqa-crossing-format-boundaries-with-a	76.2
unifiedqa-crossing-format-boundaries-with-a	62.5
commonsenseqa-a-question-answering-challenge	55.9
grapeqa-graph-augmentation-and-pruning-to	73.5
unicorn-on-rainbow-a-universal-commonsense	79.3
star-bootstrapping-reasoning-with-reasoning	60.0
albert-a-lite-bert-for-self-supervised	76.5
star-bootstrapping-reasoning-with-reasoning	55.6
human-parity-on-commonsenseqa-augmenting-self	89.4
star-bootstrapping-reasoning-with-reasoning	20.9
unifying-language-learning-paradigms	55.7
qa-gnn-reasoning-with-language-models-and	76.1