Uncertainty Quantification on ArabicaQA
0.711AUROCP(true)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| P(true)Model=Qwen2026.06 | 0.711 | — | |
| LogProbModel=Gemma2026.06 | 0.689 | — | |
| GLU-AUModel=Gemma2026.06 | 0.65 | — | |
| GLUModel=Gemma2026.06 | 0.647 | — | |
| RAUQModel=Gemma2026.06 | 0.642 | — | |
| LogProbModel=Qwen2026.06 | 0.625 | — | |
| LogProbModel=Fanar2026.06 | 0.619 | — | |
| RAUQModel=Fanar2026.06 | 0.613 | — | |
| RAUQModel=Qwen2026.06 | 0.61 | — | |
| P(true)Model=Gemma2026.06 | 0.597 | — | |
| P(true)Model=Fanar2026.06 | 0.594 | — | |
| GLU-AUModel=Fanar2026.06 | 0.586 | — | |
| GLUModel=Fanar2026.06 | 0.563 | — | |
| GLU-AUModel=Qwen2026.06 | 0.562 | — | |
| GLUModel=Qwen2026.06 | 0.556 | — | |
| LogTokUModel=Gemma2026.06 | 0.538 | — | |
| LogTokUModel=Qwen2026.06 | 0.521 | — | |
| LogTokUModel=Fanar2026.06 | 0.49 | — | |
| GLUModel=Qwen2026.06 | — | 0.14 | |
| GLUModel=Gemma2026.06 | — | 0.322 | |
| GLUModel=Fanar2026.06 | — | 0.143 | |
| GLU-AUModel=Qwen2026.06 | — | 0.16 | |
| GLU-AUModel=Gemma2026.06 | — | 0.323 | |
| GLU-AUModel=Fanar2026.06 | — | 0.194 | |
| LogProbModel=Qwen2026.06 | — | 0.201 | |
| LogProbModel=Gemma2026.06 | — | 0.343 | |
| LogProbModel=Fanar2026.06 | — | 0.254 | |
| LogTokUModel=Qwen2026.06 | — | -0.028 | |
| LogTokUModel=Gemma2026.06 | — | 0.099 | |
| LogTokUModel=Fanar2026.06 | — | -0.025 | |
| P(true)Model=Qwen2026.06 | — | 0.379 | |
| P(true)Model=Gemma2026.06 | — | 0.152 | |
| P(true)Model=Fanar2026.06 | — | 0.148 | |
| RAUQModel=Qwen2026.06 | — | 0.186 | |
| RAUQModel=Gemma2026.06 | — | 0.277 | |
| RAUQModel=Fanar2026.06 | — | 0.239 |