One Model, Two Markets: Bid-Aware Generative Recommendation

2026-03-23

AI Summary

Existing generative recommender systems struggle to simultaneously optimize semantic relevance and advertising revenue. To address this challenge, this work proposes GEM-Rec, a unified framework that decouples ad exposure decisions from item selection through learnable control tokens and introduces a bid-aware decoding mechanism that preserves ranking order. This approach dynamically incorporates real-time bidding signals into the generation process without requiring model retraining, thereby increasing the likelihood of displaying high-bid advertisements while maintaining semantic recommendation quality. Experimental results demonstrate that GEM-Rec effectively balances platform revenue and user-side relevance, significantly enhancing the performance of commercial recommender systems.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Natural Language Processing: Generation
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Ad search and search for Web retail
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

Generative Recommender Systems using semantic ids, such as TIGER (Rajput et al., 2023), have emerged as a widely adopted competitive paradigm in sequential recommendation. However, existing architectures are designed solely for semantic retrieval and do not address concerns such as monetization via ad revenue and incorporation of bids for commercial retrieval. We propose GEM-Rec, a unified framework that integrates commercial relevance and monetization objectives directly into the generative sequence. We introduce control tokens to decouple the decision of whether to show an ad from which item to show. This allows the model to learn valid placement patterns directly from interaction logs, which inherently reflect past successful ad placements. Complementing this, we devise a Bid-Aware Decoding mechanism that handles real-time pricing, injecting bids directly into the inference process to steer the generation toward high-value items. We prove that this approach guarantees allocation monotonicity, ensuring that higher bids weakly increase an ad's likelihood of being shown without requiring model retraining. Experiments demonstrate that GEM-Rec allows platforms to dynamically optimize for semantic relevance and platform revenue.

Problem

• Generative Recommendation
• Monetization
• Bid Integration
• Commercial Retrieval
• Ad Revenue

Innovation

• Generative Recommendation
• Bid-Aware Decoding
• Control Tokens
• Allocation Monotonicity
• Commercial Retrieval