Real-time Ad retrieval via LLM-generative Commercial Intention for Sponsored Search Advertising

2025-04-02

AI Summary

Existing LLM-based retrieval methods suffer from low semantic efficiency and poor scalability due to sparse one-to-few mappings between document IDs and content, coupled with costly content extraction. This paper proposes RARE, a real-time advertising retrieval framework that introduces generative “Commercial Intent” (CI) text as a lightweight semantic intermediary—replacing both DocIDs and raw content. RARE employs a domain-customized LLM infused with commercial knowledge to generate CIs and constructs a many-to-many CI–ad index, enabling efficient, scalable, low-latency recall. Deployed in production, RARE supports over one million queries per second (QPS), processing hundreds of millions of requests daily. Online A/B tests demonstrate statistically significant improvements: +5.04% in consumption, +6.37% in GMV, +1.28% in CTR, and +5.29% in shallow conversion rate. Offline evaluations show RARE outperforms ten state-of-the-art baseline models.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Ad search and search for Web retail
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The integration of Large Language Models (LLMs) with retrieval systems has shown promising potential in retrieving documents (docs) or advertisements (ads) for a given query. Existing LLM-based retrieval methods generate numeric or content-based DocIDs to retrieve docs/ads. However, the one-to-few mapping between numeric IDs and docs, along with the time-consuming content extraction, leads to semantic inefficiency and limits scalability in large-scale corpora. In this paper, we propose the Real-time Ad REtrieval (RARE) framework, which leverages LLM-generated text called Commercial Intentions (CIs) as an intermediate semantic representation to directly retrieve ads for queries in real-time. These CIs are generated by a customized LLM injected with commercial knowledge, enhancing its domain relevance. Each CI corresponds to multiple ads, yielding a lightweight and scalable set of CIs. RARE has been implemented in a real-world online system, handling daily search volumes in the hundreds of millions. The online implementation has yielded significant benefits: a 5.04% increase in consumption, a 6.37% rise in Gross Merchandise Volume (GMV), a 1.28% enhancement in click-through rate (CTR) and a 5.29% increase in shallow conversions. Extensive offline experiments show RARE's superiority over ten competitive baselines in four major categories.

Problem

• Improves ad retrieval efficiency using LLM-generated Commercial Intentions
• Addresses semantic inefficiency in large-scale ad corpora
• Enhances real-time ad relevance for sponsored search queries

Innovation

• LLM-generated Commercial Intentions for ad retrieval
• Customized LLM with commercial knowledge injection
• Lightweight scalable semantic representation for real-time retrieval