Knowledge-intensive QA on SQuAD 5-shot
90.38EM AccuracyADAFUSE (Top-2 Base)
Evaluation Results
| Method | Links | |
|---|---|---|
| ADAFUSE (Top-2 Base)Base model selection strategy=Oracle top-2 base selection2026.01 | 90.38 | |
| ADAFUSE (Fixed Base)Base model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 90.15 | |
| SWEETSPANBase model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 86.58 | |
| Mistral-7B-Instruct-v0.3Model Type=Base Model2026.01 | 83.49 | |
| UniTEBase model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 82.17 | |
| LLM-BLENDERBase model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 82.13 | |
| InternLM3-8B-InstructModel Type=Base Model2026.01 | 81.77 | |
| LLaMA-3.1-8B-InstructModel Type=Base Model2026.01 | 80.13 | |
| Qwen3-8BModel Type=Base Model2026.01 | 76.72 | |
| DEEPENBase model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 71.51 |