Multiple Choice Question Answering on CS
55.8AccuracyLoRA
Evaluation results
| Method | Links | ||
|---|---|---|---|
| LoRABackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 55.8 | 21.03 | |
| LABackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 54.71 | 13.72 | |
| MC DropBackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 54.41 | 20.83 | |
| EnsembleBackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 53.81 | 14.03 | |
| UQ4CTBackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA, Number of forward passes=12024.10 | 53.3 | 10.83 | |
| MixLoRABackbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 53.11 | 17.13 | |
| BLoB(N=10)Backbone=Llama3.1-8B, Fine-tuned Dataset=OBQA, Number of forward passes=102024.10 | 52.81 | 11.52 | |
| BLoB(Mean)Backbone=Llama3.1-8B, Fine-tuned Dataset=OBQA2024.10 | 51.2 | 17.22 |