让大模型自己决定广告投放，兼顾广告主和用户体验。
LLM-Auction: Generative Auction towards LLM-Native Advertising
- 用大模型直接生成广告内容并自动分配，无需额外推理开销。
- 在模拟环境中效率超越现有方法，同时满足公平性要求。
- 适合研究广告与大模型融合、机制设计的学者和工程师。
大语言模型应用的商业化是在线广告的新前沿，其中基于大模型原生的广告模式通过将广告融入大模型生成内容中展现出巨大潜力。然而，传统拍卖机制不再适用——拍卖对象从离散广告位转变为大模型输出的分布，且现有方法因忽略外部性或推理成本过高，在工业场景中不实用。为此，我们提出 LLM-Auction，首个基于学习的生成式拍卖机制，将拍卖与生成过程深度融合。通过将分配问题建模为大模型输出与机制目标之间的偏好对齐，使大模型在生成时自然内化分配的外部性，无需额外推理开销。理论上，我们证明了该机制具有分配单调性和连续性，并指出简单的一价支付规则具备良好激励性质。此外，我们构建了以大模型为裁判的仿真评估环境，实验表明 LLM-Auction 在分配效率上达到当前最优水平，同时满足关键机制属性。
原文摘要 · Abstract (English)
The commercialization of LLM applications is the next frontier in online advertising, with LLM-native advertising emerging as a promising paradigm by integrating ads into LLM-generated content. However, classic mechanisms are no longer applicable in this setting where the auction object is shifted from discrete ad slots to distributions over LLM outputs, and existing methods are impractical in industrial scenarios due to ignored externalities or high inference costs. To address these issues, we propose LLM-Auction, the first learning-based generative auction mechanism that integrates auction and generation. By formulating the allocation as preference alignment between LLM outputs and a mechanism objective that balances advertisers' value and user experience, we optimize the LLMs to inherently model allocation externalities without extra inference cost. Theoretically, we identify the allocation monotonicity and continuity of LLM-Auction, and prove that a simple first-price payment rule exhibits favorable incentive properties. Furthermore, we build an LLM-as-a-judge simulation environment for quantitative evaluation, and experiments demonstrate that LLM-Auction achieves the state-of-the-art allocation efficiency while satisfying key mechanism properties.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。