Semantic Uncertainty Quantification on NQ (test)
0.758AUROCTS
Evaluation Results
| Method | Links | |
|---|---|---|
| TSSC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.758 | |
| TSSC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.751 | |
| SESC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.75 | |
| SESC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.749 | |
| SESC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.745 | |
| SESC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.745 | |
| PlattSC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.745 | |
| TSSC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.745 | |
| PlattSC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.744 | |
| PlattSC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.744 | |
| PlattSC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.743 | |
| ATSSC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.743 | |
| ATSSC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.741 | |
| ATSSC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.74 | |
| ATSSC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.74 | |
| TSSC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.737 | |
| BaseSC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.691 | |
| BaseSC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.69 | |
| BaseSC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.689 | |
| BaseSC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 0.689 |