LLMs for User Interest Exploration in Large-scale Recommendation Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911910478217216 |
|---|---|
| author | Wang, Jianling Lu, Haokai Liu, Yifan Ma, He Wang, Yueqi Gu, Yang Zhang, Shuzhou Han, Ningren Bi, Shuchao Baugher, Lexi Chi, Ed Chen, Minmin |
| author_facet | Wang, Jianling Lu, Haokai Liu, Yifan Ma, He Wang, Yueqi Gu, Yang Zhang, Shuzhou Han, Ningren Bi, Shuchao Baugher, Lexi Chi, Ed Chen, Minmin |
| contents | Traditional recommendation systems are subject to a strong feedback loop by learning from and reinforcing past user-item interactions, which in turn limits the discovery of novel user interests. To address this, we introduce a hybrid hierarchical framework combining Large Language Models (LLMs) and classic recommendation models for user interest exploration. The framework controls the interfacing between the LLMs and the classic recommendation models through "interest clusters", the granularity of which can be explicitly determined by algorithm designers. It recommends the next novel interests by first representing "interest clusters" using language, and employs a fine-tuned LLM to generate novel interest descriptions that are strictly within these predefined clusters. At the low level, it grounds these generated interests to an item-level policy by restricting classic recommendation models, in this case a transformer-based sequence recommender to return items that fall within the novel clusters generated at the high level. We showcase the efficacy of this approach on an industrial-scale commercial platform serving billions of users. Live experiments show a significant increase in both exploration of novel interests and overall user enjoyment of the platform. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_16363 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLMs for User Interest Exploration in Large-scale Recommendation Systems Wang, Jianling Lu, Haokai Liu, Yifan Ma, He Wang, Yueqi Gu, Yang Zhang, Shuzhou Han, Ningren Bi, Shuchao Baugher, Lexi Chi, Ed Chen, Minmin Information Retrieval Artificial Intelligence Traditional recommendation systems are subject to a strong feedback loop by learning from and reinforcing past user-item interactions, which in turn limits the discovery of novel user interests. To address this, we introduce a hybrid hierarchical framework combining Large Language Models (LLMs) and classic recommendation models for user interest exploration. The framework controls the interfacing between the LLMs and the classic recommendation models through "interest clusters", the granularity of which can be explicitly determined by algorithm designers. It recommends the next novel interests by first representing "interest clusters" using language, and employs a fine-tuned LLM to generate novel interest descriptions that are strictly within these predefined clusters. At the low level, it grounds these generated interests to an item-level policy by restricting classic recommendation models, in this case a transformer-based sequence recommender to return items that fall within the novel clusters generated at the high level. We showcase the efficacy of this approach on an industrial-scale commercial platform serving billions of users. Live experiments show a significant increase in both exploration of novel interests and overall user enjoyment of the platform. |
| title | LLMs for User Interest Exploration in Large-scale Recommendation Systems |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2405.16363 |