Factuality Evaluation on FACTOR
75.55FACTOR ScoreSLED
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| SLEDBackbone=Mixtral-8×7B-IT2024.11 | 75.55 | — | — | |
| SLEDBackbone=Mixtral-8×7B2024.11 | 74.92 | — | — | |
| Mixtral-8×7B2024.11 | 71.41 | — | — | |
| Mixtral-8×7B-IT2024.11 | 70.51 | — | — | |
| SLEDBackbone=Gemma-7B2024.11 | 65.56 | — | — | |
| SLEDBackbone=Qwen-3-14B-Base2024.11 | 64.09 | — | — | |
| Gemma-7B2024.11 | 60.42 | — | — | |
| DoLaBackbone=Qwen-3-14B-Base2024.11 | 58.42 | — | — | |
| DoLaBackbone=Mixtral-8×7B2024.11 | 58.28 | — | — | |
| Qwen-3-14B-Base2024.11 | 57.69 | — | — | |
| SLEDBackbone=Gemma-2B2024.11 | 57.05 | — | — | |
| DoLaBackbone=Mixtral-8×7B-IT2024.11 | 56.15 | — | — | |
| SLEDBackbone=gpt-oss-20b2024.11 | 55.31 | — | — | |
| Gemma-2B2024.11 | 50.87 | — | — | |
| DoLaBackbone=gpt-oss-20b2024.11 | 43.59 | — | — | |
| gpt-oss-20b2024.11 | 41.12 | — | — | |
| DoLaBackbone=Gemma-7B2024.11 | 36.07 | — | — | |
| DoLaBackbone=Gemma-2B2024.11 | 32.93 | — | — | |
| 13b-CDBackbone=LLaMA-7b2025.03 | — | 64.11 | 61.9 | |
| AlpacaBackbone=LLaMA-7b2025.03 | — | 57.11 | 58.2 | |
| DoLaBackbone=LLaMA-7b2025.03 | — | 61.96 | 61.68 | |
| DoLaBackbone=LLaMA2-7b2025.03 | — | 63.25 | 72.68 | |
| HICDBackbone=LLaMA-7b2025.03 | — | 60.58 | 61.97 | |
| HICDBackbone=LLaMA2-7b2025.03 | — | 60.69 | 73.46 | |
| VanillaBackbone=LLaMA-7b2025.03 | — | 58.55 | 58.4 | |
| VanillaBackbone=LLaMA2-7b2025.03 | — | 58.98 | 72.03 |