Multiple Choice Question Answering on Eng
61.13AccuracyUQ4CT
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| UQ4CTBackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA, Number of forward passes=12024.10 | 61.13 | 13.21 | |
| MixLoRABackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 54.72 | 17.82 | |
| LoRABackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 54.33 | 24.13 | |
| MC DropBackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 54.11 | 24.1 | |
| LABackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 53.62 | 15.52 | |
| EnsembleBackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 52.4 | 17.41 | |
| BLoB(N=10)Backbone=Llama3.1-8B, Fine-tuned Dataset=OBQA, Number of forward passes=102024.10 | 51.93 | 14.91 | |
| BLoB(Mean)Backbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 48.61 | 18.52 |