Question Answering On Social Iqa
评估指标
Accuracy
评测结果
各个模型在此基准测试上的表现结果
比较表格
| 模型名称 | Accuracy |
|---|---|
| llama-open-and-efficient-foundation-language-1 | 50.4 |
| llama-open-and-efficient-foundation-language-1 | 48.9 |
| unifiedqa-crossing-format-boundaries-with-a | 79.8 |
| training-compute-optimal-large-language | 51.3 |
| llama-open-and-efficient-foundation-language-1 | 52.3 |
| two-is-better-than-many-binary-classification | 80.2 |
| roberta-a-robustly-optimized-bert-pretraining | 76.7 |
| two-is-better-than-many-binary-classification | 79.9 |
| mixlora-enhancing-large-language-models-fine | 78.8 |
| task-compass-scaling-multi-task-pre-training | 82.2 |
| mixture-of-subspaces-in-low-rank-adaptation | 81.0 |
| socialiqa-commonsense-reasoning-about-social | 33.3 |
| scaling-language-models-methods-analysis-1 | 50.6 |
| socialiqa-commonsense-reasoning-about-social | 63.1 |
| task-compass-scaling-multi-task-pre-training | 79.6 |
| socialiqa-commonsense-reasoning-about-social | 64.5 |
| socialiqa-commonsense-reasoning-about-social | 63 |
| mixlora-enhancing-large-language-models-fine | 82.5 |
| llama-open-and-efficient-foundation-language-1 | 50.4 |
| task-compass-scaling-multi-task-pre-training | 81.7 |
| textbooks-are-all-you-need-ii-phi-1-5 | 52.6 |
| mixlora-enhancing-large-language-models-fine | 78 |
| textbooks-are-all-you-need-ii-phi-1-5 | 53.0 |
| unicorn-on-rainbow-a-universal-commonsense | 83.2 |