🤖 AI Summary
This work addresses the challenge that embedding advertisements in large language models often compromises content fidelity and user experience, while existing approaches fail to jointly optimize ad revenue and semantic quality. The paper proposes the first framework that explicitly incorporates content fidelity into ad mechanism design by leveraging retrieval-augmented generation (RAG) to preserve response quality. It introduces an endogenous reserve price to exclude ads yielding non-positive marginal social welfare and combines a KL-regularized single-slot allocation mechanism with a screening-based VCG multi-slot mechanism to guarantee incentive compatibility and individual rationality. Experimental results demonstrate that the proposed method consistently outperforms baseline approaches across diverse scenarios, achieving superior performance in both per-ad revenue and semantic similarity to ad-free responses.
📝 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.