Data Size Saving on Empirical Setting I
77.7Data Size Saving (%)AAE
Evaluation Results
| Method | Links | |
|---|---|---|
| AAEModel=GPT-4o Fine-tuned, Prompt=Basic, m (Primary set size)=502024.12 | 77.7 | |
| AAEModel=GPT-4, Prompt=Basic, m (Primary set size)=502024.12 | 77.33 | |
| AAEModel=GPT-4o, Prompt=FS, m (Primary set size)=502024.12 | 77.15 | |
| AAEModel=GPT-4o, Prompt=COT, m (Primary set size)=502024.12 | 76.71 | |
| AAEModel=GPT-4, Prompt=COT, m (Primary set size)=502024.12 | 76.36 | |
| AAEModel=GPT-4o, Prompt=Basic, m (Primary set size)=502024.12 | 76.21 | |
| AAEModel=GPT-3.5-Turbo-0125, Prompt=COT, m (Primary set size)=502024.12 | 74.25 | |
| AAEModel=GPT-3.5-Turbo-0613, Prompt=COT, m (Primary set size)=502024.12 | 73.58 | |
| AAEModel=GPT-3.5-Turbo-0613, Prompt=Basic, m (Primary set size)=502024.12 | 69.13 | |
| AAEModel=GPT-3.5-Turbo-0125, Prompt=Basic, m (Primary set size)=502024.12 | 67.72 | |
| AAEModel=GPT-4o Fine-tuned, Prompt=Basic, m (Primary set size)=1002024.12 | 54.49 | |
| AAEModel=GPT-4, Prompt=Basic, m (Primary set size)=1002024.12 | 49.29 | |
| AAEModel=GPT-4o, Prompt=FS, m (Primary set size)=1002024.12 | 48.78 | |
| AAEModel=GPT-4, Prompt=COT, m (Primary set size)=1002024.12 | 47.92 | |
| AAEModel=GPT-4o, Prompt=Basic, m (Primary set size)=1002024.12 | 47.07 | |
| AAEModel=GPT-4o, Prompt=COT, m (Primary set size)=1002024.12 | 46.94 | |
| AAEModel=GPT-3.5-Turbo-0613, Prompt=COT, m (Primary set size)=1002024.12 | 45.95 | |
| AAEModel=GPT-3.5-Turbo-0125, Prompt=COT, m (Primary set size)=1002024.12 | 44.75 | |
| AAEModel=GPT-4o Fine-tuned, Prompt=Basic, m (Primary set size)=1502024.12 | 43.56 | |
| AAEModel=GPT-3.5-Turbo-0613, Prompt=Basic, m (Primary set size)=1002024.12 | 37.53 | |
| AAEModel=GPT-3.5-Turbo-0125, Prompt=Basic, m (Primary set size)=1002024.12 | 36.97 | |
| AAEModel=GPT-4o, Prompt=FS, m (Primary set size)=1502024.12 | 34.86 | |
| AAEModel=GPT-4, Prompt=Basic, m (Primary set size)=1502024.12 | 33.31 | |
| AAEModel=GPT-4o, Prompt=COT, m (Primary set size)=1502024.12 | 29.92 | |
| AAEModel=GPT-4, Prompt=COT, m (Primary set size)=1502024.12 | 29.47 | |
| AAEModel=GPT-4o, Prompt=Basic, m (Primary set size)=1502024.12 | 28.6 | |
| AAEModel=GPT-3.5-Turbo-0613, Prompt=COT, m (Primary set size)=1502024.12 | 25.21 | |
| AAEModel=GPT-3.5-Turbo-0125, Prompt=COT, m (Primary set size)=1502024.12 | 22.71 | |
| AAEModel=GPT-4o Fine-tuned, Prompt=Basic, m (Primary set size)=2002024.12 | 18.71 | |
| AAEModel=GPT-3.5-Turbo-0125, Prompt=Basic, m (Primary set size)=1502024.12 | 12.91 | |
| AAEModel=GPT-3.5-Turbo-0613, Prompt=Basic, m (Primary set size)=1502024.12 | 12.79 | |
| AAEModel=GPT-4, Prompt=Basic, m (Primary set size)=2002024.12 | 10.44 | |
| AAEModel=GPT-4o, Prompt=FS, m (Primary set size)=2002024.12 | 6.8 | |
| AAEModel=GPT-4, Prompt=COT, m (Primary set size)=2002024.12 | 3.6 | |
| AAEModel=GPT-4o, Prompt=COT, m (Primary set size)=2002024.12 | 3.15 | |
| AAEModel=GPT-4o, Prompt=Basic, m (Primary set size)=2002024.12 | 0.58 | |
| AAEModel=GPT-3.5-Turbo-0125, Prompt=COT, m (Primary set size)=2002024.12 | -3.78 | |
| AAEModel=GPT-3.5-Turbo-0613, Prompt=COT, m (Primary set size)=2002024.12 | -5.31 | |
| AAEModel=GPT-3.5-Turbo-0613, Prompt=Basic, m (Primary set size)=2002024.12 | -17.93 | |
| AAEModel=GPT-3.5-Turbo-0125, Prompt=Basic, m (Primary set size)=2002024.12 | -18.98 |