General Instruction Following Evaluation on Aggregated Multi-Task Suite
8.57Average Normalized ScoreEPI
Evaluation Results
| Method | Links | |
|---|---|---|
| EPIBase Model=Gemma-2-9B, Number of runs=32026.04 | 8.57 | |
| Static IsolationBase Model=Gemma-2-9B, Number of runs=32026.04 | 8.21 | |
| EPIBase Model=LLaMA-3-8B, Number of runs=32026.04 | 7.98 | |
| Full SFTBase Model=Gemma-2-9B, Number of runs=32026.04 | 7.78 | |
| Static IsolationBase Model=LLaMA-3-8B, Number of runs=32026.04 | 7.68 | |
| Full SFTBase Model=LLaMA-3-8B, Number of runs=32026.04 | 7.32 |