用多头提前退出优化RAG增强的推荐系统，兼顾速度与准确率。
The Efficiency vs. Accuracy Trade-off: Optimizing RAG-Enhanced LLM Recommender Systems Using Multi-Head Early Exit
- 引入多头提前退出机制，根据置信度动态终止推理过程。
- 实验显示计算时间显著降低，同时保持甚至提升点击率预测准确率。
- 适合追求实时响应的商业推荐系统部署场景。
将大语言模型（LLMs）应用于推荐系统以预测点击率（CTR）时，需在计算效率与预测精度之间取得平衡。本文提出一种融合检索增强生成（RAG）与创新多头提前退出架构的优化框架，同时提升两者表现。通过采用图卷积网络（GCNs）作为高效检索机制，显著缩短数据检索时间，同时维持高模型性能。提前退出策略利用多头预测置信度进行实时评估，动态终止模型推理，不仅加快了大语言模型的响应速度，还保持或提升了其准确性，适用于实时应用场景。实验表明，该架构有效减少计算耗时，且不牺牲可靠推荐所需的精度，为商业系统中高效、实时的大型语言模型部署树立新标准。
原文摘要 · Abstract (English)
The deployment of Large Language Models (LLMs) in recommender systems for predicting Click-Through Rates (CTR) necessitates a delicate balance between computational efficiency and predictive accuracy. This paper presents an optimization framework that combines Retrieval-Augmented Generation (RAG) with an innovative multi-head early exit architecture to concurrently enhance both aspects. By integrating Graph Convolutional Networks (GCNs) as efficient retrieval mechanisms, we are able to significantly reduce data retrieval times while maintaining high model performance. The early exit strategy employed allows for dynamic termination of model inference, utilizing real-time predictive confidence assessments across multiple heads. This not only quickens the responsiveness of LLMs but also upholds or improves their accuracy, making it ideal for real-time application scenarios. Our experiments demonstrate how this architecture effectively decreases computation time without sacrificing the accuracy needed for reliable recommendation delivery, establishing a new standard for efficient, real-time LLM deployment in commercial systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。