Table 4 Performance comparison with different modality inputs. The best results are in bold and the second-best results are italics.The improvement is calculated over the second-best result.

From: Leveraging multimodal large language model for multimodal sequential recommendation

Metrics

Recall@5

Recall@10

NDCG@5

NDCG@10

MRR@5

MRR@10

Text-only

0.0584

0.0648

0.03090

0.0457

0.0238

0.0299

Image-only

0.0525

0.0679

0.0689

0.0844

0.1012

0.1490

Text + Image

0.0620

0.0984

0.0733

0.0893

0.1100

0.1593

%Improv.

6.16%

4.78%

6.39%

5.81%

8.91%

6.91%

Back to article page