Commonsense Reasoning on NumerSense (test)
72.47AccuracyGenerated Knowledge Prompting
Evaluation results
| Method | Links | |
|---|---|---|
| Generated Knowledge PromptingInference Model=T5-11b2021.10 | 72.47 | |
| T5-11b 1.1 +digitsNote=Previous SOTA2021.10 | 66.18 | |
| Retrieval-based knowledgeInference Model=T5-11b2021.10 | 65.1 | |
| Vanilla baselineInference Model=T5-11b2021.10 | 64.05 |