Ad Auctions for LLMs via Retrieval Augmented Generation

TL;DR

This paper proposes novel auction mechanisms integrated with retrieval-augmented generation to allocate ads within large language model outputs, balancing efficiency, fairness, and incentivization.

Contribution

It introduces a segment auction framework for LLMs that maximizes logarithmic social welfare and extends to multi-ad scenarios, with theoretical and empirical validation.

Findings

Maximizes logarithmic social welfare in ad allocation

Characterizes incentive-compatible pricing rules

Demonstrates tradeoffs between flexibility and metrics in ad placement

Abstract

In the field of computational advertising, the integration of ads into the outputs of large language models (LLMs) presents an opportunity to support these services without compromising content integrity. This paper introduces novel auction mechanisms for ad allocation and pricing within the textual outputs of LLMs, leveraging retrieval-augmented generation (RAG). We propose a segment auction where an ad is probabilistically retrieved for each discourse segment (paragraph, section, or entire output) according to its bid and relevance, following the RAG framework, and priced according to competing bids. We show that our auction maximizes logarithmic social welfare, a new notion of welfare that balances allocation efficiency and fairness, and we characterize the associated incentive-compatible pricing rule. These results are extended to multi-ad allocation per segment. An empirical evaluation validates the feasibility and effectiveness of our approach over several ad auction scenarios, and exhibits inherent tradeoffs in metrics as we allow the LLM more flexibility to allocate ads.