Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

One Model, Two Markets: Bid-Aware Generative Recommendation

Yanchen Jiang, Zhe Feng, Christopher P. Mah, Aranyak Mehta, Di Wang

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.

One Model, Two Markets: Bid-Aware Generative Recommendation

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.
Paper Structure (45 sections, 2 theorems, 9 equations, 10 figures, 9 tables)

This paper contains 45 sections, 2 theorems, 9 equations, 10 figures, 9 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Problem Setup
  4. The GEM-Rec Framework
  5. Preliminaries: Semantic IDs
  6. Unified Sequence Construction
  7. The Factorized Generative Objective
  8. Inference-Time Bid Modulation
  9. Two-Level Logit Modulation
  10. Pricing Mechanism
  11. Theoretical Properties
  12. Hierarchical Decoding Strategy
  13. Experimental Setup
  14. Constructing the Synthetic Marketplace
  15. Evaluation Protocols
  16. ...and 30 more sections

Key Result

Proposition 1

The GEM-Allocation rule is monotone. That is, for any context $H$ and fixed opposing bids $b_{-i}$, the exposure probability $x_i(b_i, b_{-i})$ for a sponsored item $i$ is non-decreasing in $b_i$.

Figures (10)

  • Figure 1: GEM-Rec Unified Architecture. Left: training on unified organic and ad logs and sampling the slot type. Right: bid-aware decoding for ads; organic decoding stays relevance-based.
  • Figure 2: Macro-Dynamics of GEM-Rec. on the Steam dataset (a) The trade-off between Platform Utility (Revenue) and Policy Fit (NDCG with respect to the training data). We observe a frontier where significant platform utility can be generated before the model deviates significantly from the marketplace policy. (b) The parameter $\lambda$ provides monotonic control over Ad Rate.
  • Figure 3: Micro-Analysis of Recommendation Quality on the Steam dataset. (a) A validation of our central hypothesis: while NDCG drops as we force ads (Red line), the Conditional Organic NDCG (Green line) remains relatively flat. This shows that increasing $\lambda$ changes when ads are shown, but does not degrade the model's understanding of user intent for organic slots. (b) The cost of monetization: higher welfare requires displaying ads with lower semantic similarity to the user's organic target.
  • Figure 4: Full Dynamics on Beauty Dataset. Macro-dynamics (top row) and Micro-analysis (bottom row) showing consistent behavior with the Steam dataset.
  • Figure 5: Full Dynamics on Sports Dataset.
  • ...and 5 more figures

Theorems & Definitions (5)

  • Definition 4.1: GEM-Allocation Rule
  • Proposition 1: Allocative Monotonicity
  • Proposition 2: Structural Consistency
  • proof
  • proof