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

TL;DR

This paper introduces IAMFM, a framework combining incentive mechanisms with multi-fidelity optimization to improve sponsorship configuration in large language model-based advertising, balancing costs and strategic behavior.

Contribution

It proposes a novel incentive-aware multi-fidelity mechanism with efficient payment computation and formal guarantees, advancing incentive alignment in budget-constrained generative advertising.

Findings

IAMFM outperforms single-fidelity baselines across various budgets.

Active Counterfactual Optimization enables efficient payment calculation.

The framework provides formal guarantees for strategy-proofness and individual rationality.

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.