Multiple Choice Question Answering on OBQA (ACC, ECE)
0.884AccuracyUQ4CT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| UQ4CTBackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA, Number of forward passes=12024.10 | 0.884 | 3.341 | |
| MixLoRABackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 0.883 | 6.58 | |
| LoRABackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 0.8801 | 7.3 | |
| BLoB(Mean)Backbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 0.8761 | 6.83 | |
| MC DropBackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 0.8711 | 7.24 | |
| BLoB(N=10)Backbone=Llama3.1-8B, Fine-tuned Dataset=OBQA, Number of forward passes=102024.10 | 0.871 | 3.841 | |
| EnsembleBackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 0.865 | 8.63 | |
| LABackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 0.8606 | 11.975 |