LERA：基于大语言模型的生成聊天机器人广告拍卖
LERA: LLM-Enhanced RAG for Ad Auction in Generative Chatbots
AI总结：
LERA提出一种两阶段检索生成拍卖框架，通过嵌入粗过滤和LLM提示生成优化广告相关性评分，提升广告选择准确性和多样性。
摘要：
将广告拍卖机制整合到基于大语言模型（LLM）的聊天机器人中，为商业化提供了重要机会，但需在相关性、效率和用户体验之间取得平衡。最近，Feizi等人和Hajiaghayi等人提出了检索后生成范式，将检索与生成解耦，提供轻量级广告插入和支付确定。然而，当前检索仅依赖文本嵌入相似性，可能导致商业误解和重复插入问题。本文提出LERA，一种针对LLM聊天机器人的两阶段检索生成拍卖框架。第一阶段通过嵌入粗过滤预选少量候选广告商。第二阶段通过精心设计的提示查询LLM，生成候选人的logits作为优化的相关性评分。这些评分与报价结合，关键值支付规则考虑粗过滤和细排名阈值，确保对效用最大化广告商的诚实性。该框架自然扩展到动态对话流中的多个广告插入和长响应。在合成广告商-查询基准上的实验表明，LERA显著提高了广告选择准确性和插入多样性，同时仅引入可控的延迟开销。
英文摘要：
The integration of advertising auction mechanisms into large language model (LLM)-based chatbots presents a significant opportunity for commercialization, yet poses unique challenges in balancing relevance, efficiency, and user experience. Recently, Feizi et al.~\citep{feizi2023online} and Hajiaghayi et al.~\citep{hajiaghayi2024ad} outlined a retrieve-then-generate paradigm that decouples retrieval and generation, offering lightweight ad insertion and payment determination. However, current retrieval relies solely on text embedding similarity, which may lead to commercial misinterpretation and issues such as repetitive insertions. In this paper, we propose LERA, a two-stage retrieve-then-generate auction framework tailored for LLM chatbots. In the first stage, embedding-based coarse filtering pre-selects a small set of candidate advertisers. In the second stage, the LLM itself is queried with a carefully designed prompt to produce logits over candidates, which serve as refined organic relevance scores. These scores are combined with bids, and a critical-value payment rule accounts for both the coarse-filtering and fine-ranking thresholds, ensuring truthfulness for utility-maximizing advertisers. The framework naturally extends to multiple ad insertions within dynamic dialogue flows and long responses. Experiments on a synthetic advertiser-query benchmark show that LERA substantially improves ad selection accuracy and insertion diversity while incurring only controllable latency overhead.
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。
