Confidence Estimation on Global-MMLU Japanese ja (test)
74AUROCSeq. Likelihood
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Seq. LikelihoodBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.05 | 74 | 49 | 48 | 57 | |
| Verbalized Conf.Backbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.05 | 72 | 44 | 57 | 61 | |
| Cross-lingual ProbeBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.05 | 72 | 44 | 31 | 31 | |
| P(True)Backbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.05 | 54 | 24 | 21 | 21 | |
| Mass-Mean ProbeBackbone=Qwen 3 8B, Evaluation Protocol=Zero-shot2026.05 | 52 | 59 | 73 | 2 |