Hate speech classification on Measuring Hate Speech (MHS) (test)
0.819AUCxList-Hate
Evaluation results
| Method | Links | ||
|---|---|---|---|
| xList-HateModel=gemma3-4b2026.02 | 0.819 | 0.148 | |
| xList-HateModel=llama3-3b2026.02 | 0.815 | 0.124 | |
| xList-HateModel=mistral-7b2026.02 | 0.811 | 0.115 | |
| xList-HateModel=mistral-24b2026.02 | 0.796 | 0.109 | |
| xList-HateModel=gemma3-27b2026.02 | 0.779 | 0.107 | |
| xList-HateModel=gemma3-12b2026.02 | 0.762 | 0.066 | |
| xList-HateModel=llama3-8b2026.02 | 0.725 | 0.077 | |
| Zero-shotModel=mistral-7b2026.02 | 0.696 | — | |
| Zero-shotModel=gemma3-12b2026.02 | 0.696 | — | |
| Zero-shotModel=llama3-3b2026.02 | 0.691 | — | |
| Zero-shotModel=mistral-24b2026.02 | 0.686 | — | |
| Zero-shotModel=gemma3-27b2026.02 | 0.679 | — | |
| Zero-shotModel=gemma3-4b2026.02 | 0.671 | — | |
| Zero-shotModel=llama3-8b2026.02 | 0.648 | — | |
| xList-HateModel=llama3-1b2026.02 | 0.634 | 0.035 | |
| Zero-shotModel=llama3-1b2026.02 | 0.599 | — |