Knowledge-intensive QA on TriviaQA (5-shot)
82.17Exact Match AccuracyADAFUSE (Top-2 Base)
Evaluation results
| Method | Links | |
|---|---|---|
| ADAFUSE (Top-2 Base)Base model selection strategy=Oracle top-2 base selection2026.01 | 82.17 | |
| ADAFUSE (Fixed Base)Base model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 82.17 | |
| UniTEBase model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 81.38 | |
| SWEETSPANBase model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 80.75 | |
| LLaMA-3.1-8B-InstructModel Type=Base Model2026.01 | 78.97 | |
| Mistral-7B-Instruct-v0.3Model Type=Base Model2026.01 | 77.27 | |
| LLM-BLENDERBase model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 75.58 | |
| DEEPENBase model selection strategy=Fixed base pair (LLaMA-3.1-8B-Instruct and Mistral-7B-Instruct-v0.3)2026.01 | 73.85 | |
| InternLM3-8B-InstructModel Type=Base Model2026.01 | 65.38 | |
| Qwen3-8BModel Type=Base Model2026.01 | 64.72 |