Table 5 The performance of MLLM-SRec and its variants. The improvement is calculated over the base model result.
From: Leveraging multimodal large language model for multimodal sequential recommendation
Metrics | NDCG@5 | NDCG@10 | NDCG@20 | Recall@5 | Recall@10 | Recall@20 |
|---|---|---|---|---|---|---|
Base model | 0.018 | 0.0219 | 0.0285 | 0.0313 | 0.0479 | 0.0808 |
MLLM-SV | 0.0182 | 0.0225 | 0.0294 | 0.0325 | 0.0496 | 0.0819 |
MLLM-SVI | 0.0186 | 0.0227 | 0.0298 | 0.0339 | 0.0512 | 0.0841 |
MLLM-SRec | 0.0197 | 0.0242 | 0.0313 | 0.0359 | 0.0539 | 0.0876 |
%Improv. | 9.44% | 10.50% | 9.82% | 14.70% | 12.53% | 8.42% |
