Balancing Efficiency and Effectiveness: An LLM-Infused Approach for Optimized CTR Prediction
Guoxiao Zhang, Yi Wei, Yadong Zhang, Huajian Feng, Qiang Liu
TL;DR
Balancing Efficiency and Effectiveness proposes an LLM-infused framework for CTR prediction that distills deep semantic information from large language models into a compact model suitable for end-to-end training and real-time inference. The MSD framework leverages LLM-derived knowledge to capture user and item semantics while applying model compression techniques to maintain efficiency. The authors validate the approach with online A/B tests in a Meituan sponsored-search system, reporting significant improvements in CPM and CTR over strong baselines, demonstrating scalability and practical impact. The work also discusses dynamic fusion and distillation strategies to address memory and computation constraints in production CTR systems.
Abstract
Click-Through Rate (CTR) prediction is essential in online advertising, where semantic information plays a pivotal role in shaping user decisions and enhancing CTR effectiveness. Capturing and modeling deep semantic information, such as a user's preference for "Häagen-Dazs' HEAVEN strawberry light ice cream" due to its health-conscious and premium attributes, is challenging. Traditional semantic modeling often overlooks these intricate details at the user and item levels. To bridge this gap, we introduce a novel approach that models deep semantic information end-to-end, leveraging the comprehensive world knowledge capabilities of Large Language Models (LLMs). Our proposed LLM-infused CTR prediction framework(Multi-level Deep Semantic Information Infused CTR model via Distillation, MSD) is designed to uncover deep semantic insights by utilizing LLMs to extract and distill critical information into a smaller, more efficient model, enabling seamless end-to-end training and inference. Importantly, our framework is carefully designed to balance efficiency and effectiveness, ensuring that the model not only achieves high performance but also operates with optimal resource utilization. Online A/B tests conducted on the Meituan sponsored-search system demonstrate that our method significantly outperforms baseline models in terms of Cost Per Mile (CPM) and CTR, validating its effectiveness, scalability, and balanced approach in real-world applications.