Commonsense Causal Reasoning on COPA (dev)
93AccuracyGLaM
Evaluation results
| Method | Links | |
|---|---|---|
| GLaMModel Size=64B/64E, Evaluation Protocol=Few-shot, Shots=162021.12 | 93 | |
| GLaMModel Size=64B/64E, Evaluation Protocol=One-shot2021.12 | 92 | |
| GPT-3Model Size=175B, Evaluation Protocol=Few-shot, Shots=322021.12 | 92 | |
| GPT-3Model Size=175B, Evaluation Protocol=Zero-shot2021.12 | 91 | |
| GLaMModel Size=64B/64E, Evaluation Protocol=Zero-shot2021.12 | 90 | |
| GPT-3Model Size=175B, Evaluation Protocol=One-shot2021.12 | 87 | |
| KELMBackbone=BERT-large, Knowledge Source=WordNet2021.09 | 76.1 |