Question Answering On Storycloze

Accuracy

Results

Performance results of various models on this benchmark

Comparison Table

Model Name	Accuracy
efficient-language-modeling-with-sparse-all	73.3
crosslingual-generalization-through-multitask	96.3
efficient-language-modeling-with-sparse-all	67.9
massive-language-models-can-be-accurately	76.19
the-cot-collection-improving-zero-shot-and	94.5
finetuned-language-models-are-zero-shot	94.7
massive-language-models-can-be-accurately	78.87
language-models-are-few-shot-learners	72.4
finetuned-language-models-are-zero-shot	93.4
massive-language-models-can-be-accurately	77.02
unimelb-at-semeval-2016-tasks-4a-and-4b-an	78.7
improving-language-understanding-by	86.5
knowledge-in-context-towards-knowledgeable	94.40
a-simple-and-effective-approach-to-the-story	76.5
efficient-language-modeling-with-sparse-all	74.7
improving-machine-reading-comprehension-with	88.3
story-comprehension-for-predicting-what	77.6
massive-language-models-can-be-accurately	79.82
efficient-language-modeling-with-sparse-all	64.7
efficient-language-modeling-with-sparse-all	61.4
massive-language-models-can-be-accurately	47.10
guess-the-instruction-making-language-models	95.88
exploring-the-benefits-of-training-expert	86.33