Booth 21-25 | AI Data Management Zone | Tokyo Big Sight
Most AI text detectors look good in testing. They’re trained and evaluated on specific models, specific prompt styles, specific domains — and they perform well within that distribution. Then they
If you’ve worked on NLP for low-resource languages — Yoruba, Quechua, Tigrinya, Hmong — you know the math is brutal. Native speakers with domain expertise are scarce. Their time is expensive. The data needs are enormous. And you can’t bootstrap from a “close enough” language without inheriting serious bias. A
