| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| HH-RLHF D3 (test) | DEFT-PRO | Harmlessness BLEU Score32.77 | 5 | 15d ago | |
| HH-RLHF D2 (test) | DEFT-DPO | Harmlessness BLEU20.13 | 5 | 15d ago | |
| HH-RLHF 0-shot (test) | Harmlessness BLEU62.68 | 5 | 15d ago | ||
| D_r (test) | SD v1.4 | Alignment Score0.371 | 4 | 1mo ago | |
| D_r (train) | SD v1.4 | AS0.364 | 4 | 1mo ago |