Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models

2026-04-06

AI Summary

This work addresses the core challenges in generative advertising powered by large language models—namely, advertisers’ strategic behavior and the high cost of stochastic content generation. The authors propose the Incentive-Aware Multi-Fidelity Mechanism (IAMFM), which uniquely integrates the Vickrey-Clarke-Groves (VCG) incentive framework with multi-fidelity optimization to maximize social welfare under budget constraints. IAMFM employs active counterfactual optimization to efficiently compute payments, thereby achieving approximate strategyproofness and individual rationality. Algorithmic instantiations based on elimination and modeling approaches consistently outperform single-fidelity baselines across diverse budget regimes, demonstrating IAMFM’s superior efficiency and alignment of incentives.

Abstract

Generative advertising in large language model (LLM) responses requires optimizing sponsorship configurations under two strict constraints: the strategic behavior of advertisers and the high cost of stochastic generations. To address this, we propose the Incentive-Aware Multi-Fidelity Mechanism (IAMFM), a unified framework coupling Vickrey-Clarke-Groves (VCG) incentives with Multi-Fidelity Optimization to maximize expected social welfare. We compare two algorithmic instantiations (elimination-based and model-based), revealing their budget-dependent performance trade-offs. Crucially, to make VCG computationally feasible, we introduce Active Counterfactual Optimization, a "warm-start" approach that reuses optimization data for efficient payment calculation. We provide formal guarantees for approximate strategy-proofness and individual rationality, establishing a general approach for incentive-aligned, budget-constrained generative processes. Experiments demonstrate that IAMFM outperforms single-fidelity baselines across diverse budgets.

Problem

• Generative Advertising
• Large Language Models
• Incentive Compatibility
• Multi-Fidelity Optimization
• Social Welfare

Innovation

• Incentive-Aware Multi-Fidelity Optimization
• Generative Advertising
• VCG Mechanism
• Active Counterfactual Optimization
• Large Language Models