| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| CONFLICTS | FACTCORRECTOR | ROUGE97 | 25 | 3mo ago | |
| Suppressed Samples 134 samples | CDS | CR58.2 | 14 | 26d ago | |
| CHOCOLATE FT | Factual Correction Score (GPT-4V)74.79 | 6 | 3mo ago | ||
| CHOCOLATE LLM | GPT-4V Score52.35 | 6 | 3mo ago | ||
| CHOCOLATE LVLM | Factual Correction Score (GPT-4V)61.34 | 6 | 3mo ago |