MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913542563692544 |
|---|---|
| author | Xu, Baixuan Wang, Weiqi Shi, Haochen Ding, Wenxuan Jing, Huihao Fang, Tianqing Bai, Jiaxin Liu, Xin Yu, Changlong Li, Zheng Luo, Chen Yin, Qingyu Yin, Bing Chen, Long Song, Yangqiu |
| author_facet | Xu, Baixuan Wang, Weiqi Shi, Haochen Ding, Wenxuan Jing, Huihao Fang, Tianqing Bai, Jiaxin Liu, Xin Yu, Changlong Li, Zheng Luo, Chen Yin, Qingyu Yin, Bing Chen, Long Song, Yangqiu |
| contents | Improving user experience and providing personalized search results in E-commerce platforms heavily rely on understanding purchase intention. However, existing methods for acquiring large-scale intentions bank on distilling large language models with human annotation for verification. Such an approach tends to generate product-centric intentions, overlook valuable visual information from product images, and incurs high costs for scalability. To address these issues, we introduce MIND, a multimodal framework that allows Large Vision-Language Models (LVLMs) to infer purchase intentions from multimodal product metadata and prioritize human-centric ones. Using Amazon Review data, we apply MIND and create a multimodal intention knowledge base, which contains 1,264,441 million intentions derived from 126,142 co-buy shopping records across 107,215 products. Extensive human evaluations demonstrate the high plausibility and typicality of our obtained intentions and validate the effectiveness of our distillation framework and filtering mechanism. Additional experiments reveal that our obtained intentions significantly enhance large language models in two intention comprehension tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_10701 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding Xu, Baixuan Wang, Weiqi Shi, Haochen Ding, Wenxuan Jing, Huihao Fang, Tianqing Bai, Jiaxin Liu, Xin Yu, Changlong Li, Zheng Luo, Chen Yin, Qingyu Yin, Bing Chen, Long Song, Yangqiu Computation and Language Improving user experience and providing personalized search results in E-commerce platforms heavily rely on understanding purchase intention. However, existing methods for acquiring large-scale intentions bank on distilling large language models with human annotation for verification. Such an approach tends to generate product-centric intentions, overlook valuable visual information from product images, and incurs high costs for scalability. To address these issues, we introduce MIND, a multimodal framework that allows Large Vision-Language Models (LVLMs) to infer purchase intentions from multimodal product metadata and prioritize human-centric ones. Using Amazon Review data, we apply MIND and create a multimodal intention knowledge base, which contains 1,264,441 million intentions derived from 126,142 co-buy shopping records across 107,215 products. Extensive human evaluations demonstrate the high plausibility and typicality of our obtained intentions and validate the effectiveness of our distillation framework and filtering mechanism. Additional experiments reveal that our obtained intentions significantly enhance large language models in two intention comprehension tasks. |
| title | MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understanding |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2406.10701 |