Algebraic Reasoning on AQUA (test)
30.94AccuracyInteraction-Aware Influence Function (Ours)
Evaluation Results
| Method | Links | |
|---|---|---|
| Interaction-Aware Influence Function (Ours)Base Model=Llama-3.1-8B, Evaluation Protocol=Fine-tuned, Number of Seeds=52026.05 | 30.94 | |
| RandomBase Model=Llama-3.1-8B, Evaluation Protocol=Fine-tuned, Number of Seeds=52026.05 | 24.65 | |
| RDS+Base Model=Llama-3.1-8B, Evaluation Protocol=Fine-tuned, Number of Seeds=52026.05 | 24.65 | |
| Additive IFBase Model=Llama-3.1-8B, Evaluation Protocol=Fine-tuned, Number of Seeds=52026.05 | 20.63 | |
| LESSBase Model=Llama-3.1-8B, Evaluation Protocol=Fine-tuned, Number of Seeds=52026.05 | 8.82 | |
| NV-EmbedBase Model=Llama-3.1-8B, Evaluation Protocol=Fine-tuned, Number of Seeds=52026.05 | 8.43 |