让大模型广告更公平高效，自动平衡预算与广告商激励。
Incentive-Aware Multi-Fidelity Optimization for Generative Advertising in Large Language Models
- 结合拍卖机制与多精度优化，动态调整广告配置
- 在不同预算下均优于单一精度方法，提升整体社会效益
- 适合研究广告系统、博弈机制或大模型应用的开发者
大语言模型生成广告需在广告商策略行为和随机生成高成本双重约束下优化赞助配置。为此，我们提出激励感知多精度机制（IAMFM），将维克里-克拉克-格罗夫斯（VCG）激励机制与多精度优化相结合，以最大化预期社会福利。对比基于消除和基于模型的两种算法实现，揭示其预算依赖的性能权衡。关键在于，为使VCG计算可行，引入主动反事实优化，通过复用优化数据实现高效支付计算。我们提供近似策略不变性和个体理性形式保证，建立了一种激励对齐、预算受限的生成流程通用方法。实验表明，IAMFM在多种预算下均优于单精度基线。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。