Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning
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_ | 1866913568082886656 |
|---|---|
| author | Bao, Keqin Yan, Ming Zhang, Yang Zhang, Jizhi Wang, Wenjie Feng, Fuli He, Xiangnan |
| author_facet | Bao, Keqin Yan, Ming Zhang, Yang Zhang, Jizhi Wang, Wenjie Feng, Fuli He, Xiangnan |
| contents | Frequently updating Large Language Model (LLM)-based recommender systems to adapt to new user interests -- as done for traditional ones -- is impractical due to high training costs, even with acceleration methods. This work explores adapting to dynamic user interests without any model updates by leveraging In-Context Learning (ICL), which allows LLMs to learn new tasks from few-shot examples provided in the input. Using new-interest examples as the ICL few-shot examples, LLMs may learn real-time interest directly, avoiding the need for model updates. However, existing LLM-based recommenders often lose the in-context learning ability during recommendation tuning, while the original LLM's in-context learning lacks recommendation-specific focus. To address this, we propose RecICL, which customizes recommendation-specific in-context learning for real-time recommendations. RecICL organizes training examples in an in-context learning format, ensuring that in-context learning ability is preserved and aligned with the recommendation task during tuning.
Extensive experiments demonstrate RecICL's effectiveness in delivering real-time recommendations without requiring model updates. Our code is available at https://github.com/ym689/rec_icl. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_23136 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning Bao, Keqin Yan, Ming Zhang, Yang Zhang, Jizhi Wang, Wenjie Feng, Fuli He, Xiangnan Information Retrieval Frequently updating Large Language Model (LLM)-based recommender systems to adapt to new user interests -- as done for traditional ones -- is impractical due to high training costs, even with acceleration methods. This work explores adapting to dynamic user interests without any model updates by leveraging In-Context Learning (ICL), which allows LLMs to learn new tasks from few-shot examples provided in the input. Using new-interest examples as the ICL few-shot examples, LLMs may learn real-time interest directly, avoiding the need for model updates. However, existing LLM-based recommenders often lose the in-context learning ability during recommendation tuning, while the original LLM's in-context learning lacks recommendation-specific focus. To address this, we propose RecICL, which customizes recommendation-specific in-context learning for real-time recommendations. RecICL organizes training examples in an in-context learning format, ensuring that in-context learning ability is preserved and aligned with the recommendation task during tuning. Extensive experiments demonstrate RecICL's effectiveness in delivering real-time recommendations without requiring model updates. Our code is available at https://github.com/ym689/rec_icl. |
| title | Real-Time Personalization for LLM-based Recommendation with Customized In-Context Learning |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2410.23136 |