A Japanese toxicity detector whose headline metric is not flagging legitimate criticism (Macro F1 0.975)
TL;DR — We released ja-toxicity-guard-v1, a multi-label classifier that flags seven kinds of harmful Japanese text — insult, indirect attack, exposure intent, threat, discrimination, sexual harassment, self-harm signals. On a sealed test of 5,000 items it scores Macro F1 0.9747, and it flagged zero…
Read the full story at DEV Community — Machine Learning ↗
Timeline · 1 report
- 2026-11-19 11:14 · DEV Community — Machine Learning
A Japanese toxicity detector whose headline metric is not flagging legitimate criticism (Macro F1 0.975)