Faithfulness Evaluation on mFACE
64.7Balanced Accuracy (AM)UCS (EN)
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| UCS (EN)Backbone=Qwen-235B, Training Supervision Language=English2026.03 | 64.7 | 67.7 | 82.4 | 79 | 75.1 | 74.6 | 70 | 85.5 | 74.9 | |
| RocketEvalBackbone=Qwen-235B, Evaluator Type=Checklist-based2026.03 | 61.2 | 69.2 | 75.4 | 77 | 74.9 | 72.9 | 66.9 | 78.1 | 72 | |
| CheckEvalBackbone=Qwen-235B, Evaluator Type=Checklist-based2026.03 | 60.8 | 68.9 | 74.9 | 76.8 | 75.1 | 73.4 | 65.8 | 76.4 | 71.5 | |
| AGBackbone=Qwen-235B, Prompting Strategy=Annotation Guidelines2026.03 | 59.3 | 67.4 | 76.6 | 77.7 | 72.6 | 70.7 | 69 | 79.5 | 71.6 | |
| CoTBackbone=Qwen-235B, Prompting Strategy=Chain-of-Thought2026.03 | 58.7 | 68.5 | 72.8 | 77.5 | 71.4 | 69.2 | 69.4 | 74.4 | 70.2 | |
| Zero-shotBackbone=Qwen-235B, Prompting Strategy=Zero-shot2026.03 | 54.7 | 70.2 | 74.3 | 73 | 72.6 | 69.7 | 68 | 77.9 | 70.1 | |
| ChatEvalBackbone=Qwen-235B, Evaluator Type=Multi-agent debate2026.03 | 51.1 | 65.5 | 68.4 | 74 | 63.9 | 66.1 | 55.7 | 70.3 | 64.4 |