Text Generation On Harmfulqa
Metriken
ASR
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | ASR | Paper Title | Repository |
|---|---|---|---|
| GPT-4 | 65.1 | Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment |
0 of 1 row(s) selected.