Hate speech classification on ETHOS (test)
0.912AUCxList-Hate
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| xList-HateModel=mistral-24b2026.02 | 0.912 | 0.078 | |
| xList-HateModel=mistral-7b2026.02 | 0.908 | 0.054 | |
| xList-HateModel=gemma3-12b2026.02 | 0.902 | 0.057 | |
| xList-HateModel=gemma3-27b2026.02 | 0.902 | 0.07 | |
| xList-HateModel=llama3-3b2026.02 | 0.883 | 0.079 | |
| xList-HateModel=gemma3-4b2026.02 | 0.882 | 0.063 | |
| Zero-shotModel=mistral-7b2026.02 | 0.853 | — | |
| Zero-shotModel=gemma3-12b2026.02 | 0.845 | — | |
| Zero-shotModel=mistral-24b2026.02 | 0.834 | — | |
| Zero-shotModel=gemma3-27b2026.02 | 0.832 | — | |
| Zero-shotModel=gemma3-4b2026.02 | 0.819 | — | |
| Zero-shotModel=llama3-3b2026.02 | 0.804 | — | |
| xList-HateModel=llama3-8b2026.02 | 0.804 | 0.005 | |
| Zero-shotModel=llama3-8b2026.02 | 0.799 | — | |
| xList-HateModel=llama3-1b2026.02 | 0.724 | 0.011 | |
| Zero-shotModel=llama3-1b2026.02 | 0.713 | — |