Search papers, labs, and topics across Lattice.
This paper introduces the Incentive-Aware Multi-Fidelity Mechanism (IAMFM) to optimize sponsored content generation in LLMs while accounting for advertiser incentives and computational costs. IAMFM combines VCG mechanisms with multi-fidelity optimization, using Active Counterfactual Optimization to efficiently calculate payments and ensure approximate strategy-proofness. Experiments show IAMFM outperforms single-fidelity approaches, demonstrating improved social welfare under budget constraints.
Optimizing sponsored content in LLMs doesn't have to break the bank: IAMFM leverages multi-fidelity optimization and active counterfactuals to make VCG mechanisms computationally feasible.
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.
