LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System
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_ | 1866918093345783808 |
|---|---|
| author | Li, Fengxin Li, Yi Liu, Yue Zhou, Chao Wang, Yuan Deng, Xiaoxiang Xue, Wei Liu, Dapeng Xiao, Lei Gu, Haijie Jiang, Jie Liu, Hongyan Qin, Biao He, Jun |
| author_facet | Li, Fengxin Li, Yi Liu, Yue Zhou, Chao Wang, Yuan Deng, Xiaoxiang Xue, Wei Liu, Dapeng Xiao, Lei Gu, Haijie Jiang, Jie Liu, Hongyan Qin, Biao He, Jun |
| contents | Display advertising provides significant value to advertisers, publishers, and users. Traditional display advertising systems utilize a multi-stage architecture consisting of retrieval, coarse ranking, and final ranking. However, conventional retrieval methods rely on ID-based learning to rank mechanisms and fail to adequately utilize the content information of ads, which hampers their ability to provide diverse recommendation lists.
To address this limitation, we propose leveraging the extensive world knowledge of LLMs. However, three key challenges arise when attempting to maximize the effectiveness of LLMs: "How to capture user interests", "How to bridge the knowledge gap between LLMs and advertising system", and "How to efficiently deploy LLMs". To overcome these challenges, we introduce a novel LLM-based framework called LLM Empowered Display ADvertisement REcommender system (LEADRE). LEADRE consists of three core modules: (1) The Intent-Aware Prompt Engineering introduces multi-faceted knowledge and designs intent-aware <Prompt, Response> pairs that fine-tune LLMs to generate ads tailored to users' personal interests. (2) The Advertising-Specific Knowledge Alignment incorporates auxiliary fine-tuning tasks and Direct Preference Optimization (DPO) to align LLMs with ad semantic and business value. (3) The Efficient System Deployment deploys LEADRE in an online environment by integrating both latency-tolerant and latency-sensitive service. Extensive offline experiments demonstrate the effectiveness of LEADRE and validate the contributions of individual modules. Online A/B test shows that LEADRE leads to a 1.57% and 1.17% GMV lift for serviced users on WeChat Channels and Moments separately. LEADRE has been deployed on both platforms, serving tens of billions of requests each day. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_13789 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System Li, Fengxin Li, Yi Liu, Yue Zhou, Chao Wang, Yuan Deng, Xiaoxiang Xue, Wei Liu, Dapeng Xiao, Lei Gu, Haijie Jiang, Jie Liu, Hongyan Qin, Biao He, Jun Information Retrieval Display advertising provides significant value to advertisers, publishers, and users. Traditional display advertising systems utilize a multi-stage architecture consisting of retrieval, coarse ranking, and final ranking. However, conventional retrieval methods rely on ID-based learning to rank mechanisms and fail to adequately utilize the content information of ads, which hampers their ability to provide diverse recommendation lists. To address this limitation, we propose leveraging the extensive world knowledge of LLMs. However, three key challenges arise when attempting to maximize the effectiveness of LLMs: "How to capture user interests", "How to bridge the knowledge gap between LLMs and advertising system", and "How to efficiently deploy LLMs". To overcome these challenges, we introduce a novel LLM-based framework called LLM Empowered Display ADvertisement REcommender system (LEADRE). LEADRE consists of three core modules: (1) The Intent-Aware Prompt Engineering introduces multi-faceted knowledge and designs intent-aware <Prompt, Response> pairs that fine-tune LLMs to generate ads tailored to users' personal interests. (2) The Advertising-Specific Knowledge Alignment incorporates auxiliary fine-tuning tasks and Direct Preference Optimization (DPO) to align LLMs with ad semantic and business value. (3) The Efficient System Deployment deploys LEADRE in an online environment by integrating both latency-tolerant and latency-sensitive service. Extensive offline experiments demonstrate the effectiveness of LEADRE and validate the contributions of individual modules. Online A/B test shows that LEADRE leads to a 1.57% and 1.17% GMV lift for serviced users on WeChat Channels and Moments separately. LEADRE has been deployed on both platforms, serving tens of billions of requests each day. |
| title | LEADRE: Multi-Faceted Knowledge Enhanced LLM Empowered Display Advertisement Recommender System |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2411.13789 |