Question Answering On Pubchemqa
Metrics
BLEU-2
BLEU-4
MEATOR
ROUGE-1
ROUGE-2
ROUGE-L
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | BLEU-2 | BLEU-4 | MEATOR | ROUGE-1 | ROUGE-2 | ROUGE-L |
|---|---|---|---|---|---|---|
| biomedgpt-open-multimodal-generative-pre | 0.234 | 0.141 | 0.308 | 0.386 | 0.206 | 0.332 |
| llama-2-open-foundation-and-fine-tuned-chat | 0.075 | 0.009 | 0.149 | 0.184 | 0.043 | 0.142 |