Semantic Uncertainty Discrimination on TriviaQA
0.853E-SCTS
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| TSEvaluation Protocol=SEconf, Model=Qwen2026.04 | 0.853 | 0.865 | 0.864 | 0.851 | |
| ATSEvaluation Protocol=SEconf, Model=Qwen2026.04 | 0.843 | 0.84 | 0.838 | 0.843 | |
| PlattEvaluation Protocol=SEconf, Model=Qwen2026.04 | 0.839 | 0.84 | 0.836 | 0.839 | |
| SEEvaluation Protocol=SEconf, Model=Qwen, Temperature Scaling=tau=0.52026.04 | 0.834 | 0.833 | 0.83 | 0.834 | |
| BaseEvaluation Protocol=SEconf, Model=Qwen, Temperature Scaling=tau=1.02026.04 | 0.766 | 0.761 | 0.765 | 0.767 |