Error Detection on Bamboogle
0.94F1 ScoreEnsemble-A
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Ensemble-AModel=Qwen3-8B2026.02 | 0.94 | 0.95 | 0.94 | 0.8 | |
| Ensemble-AModel=Qwen 8B2026.02 | 0.94 | — | — | 0.8 | |
| DBA-AModel=Qwen3-8B2026.02 | 0.93 | 0.96 | 0.9 | 0.82 | |
| DBA-AModel=Qwen 8B2026.02 | 0.93 | — | — | 0.82 | |
| DBA-AModel=Llama 3.3 70B2026.02 | 0.92 | 0.94 | 0.9 | 0.91 | |
| DBA-AModel=Llama 3.3 70B2026.02 | 0.92 | — | — | 0.91 | |
| Ensemble-IModel=Qwen3-8B2026.02 | 0.9 | 0.95 | 0.85 | 0.76 | |
| Ensemble-IModel=Qwen 8B2026.02 | 0.9 | — | — | 0.76 | |
| Ensemble-AModel=Llama 3.3 70B2026.02 | 0.89 | 0.87 | 0.91 | 0.87 | |
| Ensemble-AModel=Llama 3.3 70B2026.02 | 0.89 | — | — | 0.87 | |
| Ensemble-IModel=Llama 3.3 70B2026.02 | 0.85 | 0.85 | 0.85 | 0.84 | |
| Ensemble-IModel=Llama 3.3 70B2026.02 | 0.85 | — | — | 0.84 | |
| DBA-IModel=Llama 3.3 70B2026.02 | 0.84 | 0.89 | 0.81 | 0.84 | |
| DBA-IModel=Llama 3.3 70B2026.02 | 0.84 | — | — | 0.84 | |
| DBA-IModel=Qwen3-8B2026.02 | 0.8 | 0.99 | 0.67 | 0.8 | |
| DBA-IModel=Qwen 8B2026.02 | 0.8 | — | — | 0.8 | |
| DBA-AModel=GPT 5.12026.02 | 0.73 | 0.86 | 0.63 | 0.81 | |
| AYSModel=Qwen3-8B2026.02 | 0.73 | 0.94 | 0.59 | 0.66 | |
| DBA-AModel=GPT 5.12026.02 | 0.73 | — | — | 0.81 | |
| AYSModel=Qwen 8B2026.02 | 0.73 | — | — | 0.66 | |
| Ensemble-AModel=GPT 5.12026.02 | 0.67 | 0.71 | 0.63 | 0.79 | |
| Ensemble-AModel=GPT 5.12026.02 | 0.67 | — | — | 0.79 | |
| Ensemble-IModel=GPT 5.12026.02 | 0.59 | 0.67 | 0.53 | 0.74 | |
| IC-IDKModel=Qwen3-8B2026.02 | 0.59 | 0.94 | 0.43 | 0.62 | |
| Ensemble-IModel=GPT 5.12026.02 | 0.59 | — | — | 0.74 | |
| IC-IDKModel=Qwen 8B2026.02 | 0.59 | — | — | 0.62 | |
| DBA-IModel=GPT 5.12026.02 | 0.56 | 0.69 | 0.47 | 0.72 | |
| DBA-IModel=GPT 5.12026.02 | 0.56 | — | — | 0.72 | |
| AYSModel=Llama 3.3 70B2026.02 | 0.51 | 0.81 | 0.37 | 0.63 | |
| AYSModel=Llama 3.3 70B2026.02 | 0.51 | — | — | 0.63 | |
| IC-IDKModel=Llama 3.3 70B2026.02 | 0.48 | 0.73 | 0.36 | 0.6 | |
| IC-IDKModel=Llama 3.3 70B2026.02 | 0.48 | — | — | 0.6 | |
| AYSModel=GPT 5.12026.02 | 0.47 | 0.64 | 0.37 | 0.67 | |
| AYSModel=GPT 5.12026.02 | 0.47 | — | — | 0.66 | |
| IC-IDKModel=GPT 5.12026.02 | 0.43 | 0.67 | 0.32 | 0.64 | |
| IC-IDKModel=GPT 5.12026.02 | 0.43 | — | — | 0.64 |