Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models
This addresses the challenge of incentive-aligned, budget-constrained advertising in LLMs, offering a novel framework with potential applications in generative AI systems.
The paper tackles the problem of optimizing generative advertising in large language models under constraints of advertiser strategic behavior and high generation costs, proposing the Incentive-Aware Multi-Fidelity Mechanism (IAMFM) to maximize expected social welfare with formal guarantees and outperforming baselines across budgets.
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.