Semantic Uncertainty Quantification on SQuAD (test)
74.8AUROCTS
Evaluation Results
| Method | Links | |
|---|---|---|
| TSSC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 74.8 | |
| TSSC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 71.7 | |
| TSSC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 70.7 | |
| TSSC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 70.7 | |
| SESC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 65.3 | |
| SESC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 65.3 | |
| SESC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 65.3 | |
| SESC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 65.3 | |
| PlattSC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 65.3 | |
| PlattSC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 65.3 | |
| PlattSC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 65.2 | |
| ATSSC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 65.2 | |
| PlattSC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 64.9 | |
| ATSSC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 62.4 | |
| BaseSC Measure=L-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 59.5 | |
| BaseSC Measure=IC-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 59.5 | |
| BaseSC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 59.5 | |
| BaseSC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 59 | |
| ATSSC Measure=G-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 57.8 | |
| ATSSC Measure=E-SC, Model=Qwen, Evaluation Protocol=SE_vanilla (greedy-decoding)2026.04 | 57.5 |