Mechanism Design for Quality-Preserving LLM Advertising
For LLM providers and advertisers, this work addresses the trade-off between revenue and output quality in LLM advertising, offering a principled approach to monetization without degrading user experience.
The paper proposes a quality-preserving auction framework for LLM advertising that integrates content fidelity via RAG, using KL-regularized mechanisms with Myerson payments and screened VCG to ensure incentive compatibility. Experiments show the mechanisms outperform baselines in revenue per ad and semantic similarity to no-ad responses.
Embedding advertisements into large language model (LLM) outputs introduces a fundamental tension: revenue optimization can distort content and degrade user experience. Existing approaches largely ignore this trade-off, often forcing irrelevant ads into responses. We propose a quality-preserving auction framework that explicitly integrates content fidelity into the mechanism design. Built on retrieval-augmented generation (RAG), our approach treats organic content as a reference and derives an endogenous reserve price that screens out ads with non-positive marginal social welfare contributions. We develop a KL-regularized single-allocation mechanism with Myerson payments and a screened VCG multi-allocation mechanism, both satisfying dominant-strategy incentive compatibility and individual rationality. Experiments across diverse scenarios demonstrate that our mechanisms outperform existing baselines in metrics such as revenue per ad and semantic similarity to no-ad responses. Our results establish a new paradigm for LLM advertising that enables monetization without compromising output quality.