Sponsored Questions and How to Auction Them

2025-12-03

AI Summary

Ambiguous user search intent leads to inefficient ad matching. Method: This paper proposes leveraging large language models (LLMs) to autonomously generate sponsorable clarifying follow-up queries and designs a mechanism to allocate scarce “sponsored follow-up slots.” Crucially, it jointly models sponsored follow-ups and subsequent ad auctions—introducing the first end-to-end joint optimization framework based on the Vickrey–Clarke–Groves (VCG) mechanism. Contribution/Results: Theoretical analysis proves the mechanism achieves both efficiency optimality and incentive compatibility (truthfulness), whereas conventional staged designs suffer unbounded price-of-anarchy losses. Through formal mechanism design and multi-stage game-theoretic analysis, the work demonstrates that joint optimization significantly improves system-wide efficiency and reveals that sequential approaches degrade severely due to strategic interdependencies among participants.

Technology Category

• Search and Optimization: Learning to Search
• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Mechanism Design

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• User Modeling, Personalization and Recommendation: User modeling for targeted and personalized online advertising
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Online platforms connect users with relevant products and services using ads. A key challenge is that a user's search query often leaves their true intent ambiguous. Typically, platforms passively predict relevance based on available signals and in some cases offer query refinements. The shift from traditional search to conversational AI provides a new approach. When a user's query is ambiguous, a Large Language Model (LLM) can proactively offer several clarifying follow-up prompts. In this paper we consider the following: what if some of these follow-up prompts can be ``sponsored,''i.e., selected for their advertising potential. How should these ``suggestion slots''be allocated? And, how does this new mechanism interact with the traditional ad auction that might follow? This paper introduces a formal model for designing and analyzing these interactive platforms. We use this model to investigate a critical engineering choice: whether it is better to build an end-to-end pipeline that jointly optimizes the user interaction and the final ad auction, or to decouple them into separate mechanisms for the suggestion slots and another for the subsequent ad slot. We show that the VCG mechanism can be adopted to jointly optimize the sponsored suggestion and the ads that follow; while this mechanism is more complex, it achieves outcomes that are efficient and truthful. On the other hand, we prove that the simple-to-implement modular approach suffers from strategic inefficiency: its Price of Anarchy is unbounded.

Problem

• Designing an auction mechanism for sponsored clarifying prompts in conversational AI.
• Determining optimal allocation of suggestion slots for advertising potential.
• Analyzing interaction between sponsored suggestions and traditional ad auctions.

Innovation

• LLM proactively offers clarifying prompts
• VCG mechanism jointly optimizes suggestions and ads
• Modular approach suffers from unbounded inefficiency