Mechanism Design for Quality-Preserving LLM Advertising

TL;DR

This paper introduces a novel auction framework for embedding ads into LLM outputs that balances revenue with content quality, using retrieval-augmented generation and incentive-compatible mechanisms.

Contribution

It presents a quality-preserving auction mechanism that explicitly incorporates content fidelity, ensuring monetization without degrading output quality.

Findings

Mechanisms outperform baselines in revenue per ad

They maintain semantic similarity to no-ad responses

The approach satisfies incentive compatibility and individual rationality

Abstract

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.