jev-cyrillic-audit
tonysafonov/jev-cyrillic-audit
Does TypeSafe's Jev keep its accuracy and calibration on Russian? Independent RU vs EN audit (ECE, reliability diagrams, paired bootstrap) on parallel human-labelled data.
Python
- 星标
- 0
- 派生
- 0
收录依据
README 报告了一项预注册的俄语/英语 XNLI 配对评测,称 Jev 的俄语准确率与校准度较低;本次未复现结果。