General QA Verification on NQ
86.21P@1Agentic-Generative Scorer
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Agentic-Generative ScorerBackbone=Qwen-3-4B-Instruct, AR=true, EK=true, FS=true, TE=false2026.01 | 86.21 | 79.31 | |
| DiVABackbone=Qwen-3-4B-Instruct, AR=true, EK=true, FS=true, TE=true2026.01 | 85.22 | 81.28 | |
| DiVABackbone=Qwen-2.5-7B-Instruct, AR=true, EK=true, FS=true, TE=true2026.01 | 84.24 | 82.92 | |
| DiVA w/o compressionBackbone=Qwen-2.5-7B-Instruct, AR=true, EK=true, FS=true, TE=true2026.01 | 81.28 | 77.67 | |
| Agentic-Generative ScorerBackbone=Qwen-2.5-7B-Instruct, AR=true, EK=true, FS=true, TE=false2026.01 | 79.31 | 75.7 | |
| DiVA w/o compressionBackbone=Qwen-3-4B-Instruct, AR=true, EK=true, FS=true, TE=true2026.01 | 79.31 | 78.98 | |
| Agentic-Generative VerifierBackbone=Qwen-2.5-7B-Instruct, AR=true, EK=true, FS=false, TE=true2026.01 | 77.83 | 71.43 | |
| FactScore w/ GPT-4Backbone=GPT-42026.01 | 77.64 | 70.74 | |
| Agentic-Generative VerifierBackbone=Qwen-3-4B-Instruct, AR=true, EK=true, FS=false, TE=true2026.01 | 77.34 | 71.1 | |
| MiniCheck w/ MiniCheck-7BBackbone=MiniCheck-7B2026.01 | 71.92 | 66.5 | |
| Generative VerifierBackbone=Qwen-2.5-7B-Instruct, AR=true, EK=false, FS=false, TE=true2026.01 | 71.92 | 62.56 | |
| Generative VerifierBackbone=Qwen-3-4B-Instruct, AR=true, EK=false, FS=false, TE=true2026.01 | 71.57 | 63.45 | |
| MiniCheck w/ Flan-T5Backbone=Flan-T52026.01 | 67.98 | 59.28 | |
| Discriminative VerifierBackbone=Qwen-2.5-7B-Instruct, AR=false, EK=false, FS=true, TE=true2026.01 | 67.49 | 56.32 | |
| Discriminative VerifierBackbone=Qwen-3-4B-Instruct, AR=false, EK=false, FS=true, TE=true2026.01 | 67.49 | 55.01 | |
| HHEM-2.1-Open2026.01 | 66.01 | 56.98 |