arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.09459cs.GTcs.AIcs.CLcs.LG
收藏

基于检索增强生成的大语言模型广告拍卖机制

Ad Auctions for LLMs via Retrieval Augmented Generation

University of Maryland(马里兰大学);Google Research(谷歌研究院)

MohammadTaghi Hajiaghayi, Sébastien Lahaie, Keivan Rezaei, Suho Shin

AI总结:

本研究针对大语言模型输出中的广告植入需求,提出基于RAG的分段拍卖机制,可最大化对数社会福利且满足激励相容,实验验证了其可行性并揭示了分配灵活度与指标间的权衡关系。

摘要:

在计算广告领域,将广告整合进大语言模型(LLM)的输出内容中,为在不损害内容完整性的前提下支撑这类服务运营提供了机遇。本文提出了一套依托检索增强生成(RAG)技术、在LLM文本输出中进行广告分配与定价的新型拍卖机制。我们提出了分段拍卖模式:遵循RAG框架,根据广告的出价和相关性,为每个话语片段(段落、章节或完整输出)概率性检索广告,并依据竞争出价完成定价。我们证明该拍卖机制可最大化对数社会福利——一种平衡分配效率与公平性的新型福利概念,同时刻画了对应的激励相容定价规则。这些结果还可扩展至单个片段分配多条广告的场景。实证评估验证了我们的方法在多种广告拍卖场景下的可行性与有效性,同时揭示了当我们赋予LLM更大的广告分配灵活度时,各项指标之间存在的固有权衡关系。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑