Visual Question Answering On Mmhal Bench
Metriken
Hallucination Rate
Score
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Modellname | Hallucination Rate | Score | Paper Title | Repository |
|---|---|---|---|---|
| RLAIF-V 7B | 29.2 | 3.06 | RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness | |
| RLAIF-V 12B | 29.2 | 3.36 | RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness |
0 of 2 row(s) selected.