Music Question Answering On Musicqa

BERT Score

BLEU

METEOR

ROUGE

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	BERT Score	BLEU	METEOR	ROUGE	Paper Title
LLaMA Adapter	0.895	0.273	0.334	0.413	LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
LTU	0.887	0.242	0.274	0.326	Listen, Think, and Understand
MU-LLaMA	0.901	0.306	0.385	0.466	Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning

0 of 3 row(s) selected.