Word Sense Disambiguation On Big Bench
評価指標
Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| GAL 120B (few-shot, k=5) | 48.7 | Galactica: A Large Language Model for Science | |
| BLOOM 176B | 1.3 | Galactica: A Large Language Model for Science | |
| Chinchilla-70B (few-shot, k=5) | 69.1 | Training Compute-Optimal Large Language Models | |
| GAL 30B (few-shot, k=5) | 47.0 | Galactica: A Large Language Model for Science | |
| OPT 175B | 49.1 | Galactica: A Large Language Model for Science | |
| Gopher-280B (few-shot, k=5) | 56.4 | Scaling Language Models: Methods, Analysis & Insights from Training Gopher |
0 of 6 row(s) selected.