Logical Reasoning on RP LP Domain, Npred ≤ 30, 6 < δ ≤ 12
99.5Accuracycot w. L = 64
Evaluation Results
| Method | Links | |
|---|---|---|
| cot w. L = 64Reasoning Strategy=CoT, Number of Layers=642026.05 | 99.5 | |
| cot w. L = 128Reasoning Strategy=CoT, Number of Layers=1282026.05 | 99.5 | |
| cot (baseline)Reasoning Strategy=CoT2026.05 | 98.8 | |
| cot w. L = 64Reasoning Strategy=CoT, Number of Layers=642026.05 | 98.3 | |
| cot w. L = 128Reasoning Strategy=CoT, Number of Layers=1282026.05 | 98.3 | |
| cot w. L = 96Reasoning Strategy=CoT, Number of Layers=962026.05 | 96 | |
| cot w. L = 48Reasoning Strategy=CoT, Number of Layers=482026.05 | 93.9 | |
| direct w. L = 128Reasoning Strategy=Direct, Number of Layers=1282026.05 | 93.2 | |
| cot w. L = 32Reasoning Strategy=CoT, Number of Layers=322026.05 | 92.3 | |
| cot w. L = 24Reasoning Strategy=CoT, Number of Layers=242026.05 | 91 | |
| direct w. L = 128Reasoning Strategy=Direct, Number of Layers=1282026.05 | 90.9 | |
| cot (baseline)Reasoning Strategy=CoT2026.05 | 87.1 | |
| cot w. Nepochs = 60Reasoning Strategy=CoT, N_epochs=602026.05 | 86 | |
| cot w. L = 16Reasoning Strategy=CoT, Number of Layers=162026.05 | 83.5 | |
| direct (baseline)Reasoning Strategy=Direct2026.05 | 82.8 | |
| cot w. Nepochs = 30Reasoning Strategy=CoT, N_epochs=302026.05 | 82.6 | |
| direct w. L = 64Reasoning Strategy=Direct, Number of Layers=642026.05 | 81.8 | |
| direct w. L = 96Reasoning Strategy=Direct, Number of Layers=962026.05 | 77.8 | |
| direct w. L = 48Reasoning Strategy=Direct, Number of Layers=482026.05 | 76.2 | |
| direct w. L = 32Reasoning Strategy=Direct, Number of Layers=322026.05 | 72 | |
| direct w. L = 24Reasoning Strategy=Direct, Number of Layers=242026.05 | 70 | |
| direct w. Nepochs = 30Reasoning Strategy=Direct, N_epochs=302026.05 | 66.1 | |
| direct w. Nepochs = 60Reasoning Strategy=Direct, N_epochs=602026.05 | 64.6 | |
| direct (baseline)Reasoning Strategy=Direct2026.05 | 62.7 | |
| direct w. L = 16Reasoning Strategy=Direct, Number of Layers=162026.05 | 60.3 |