用大模型指导广告关键词推荐，提升相关性与多样性
LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay
- 用LLM生成标签，通过交叉编码器蒸馏知识
- 减少点击偏差，推荐结果更符合买家和卖家需求
- 适合电商广告系统优化与搜索相关性研究
电商平台卖家需选择相关关键词以优化广告投放。关键词需兼顾卖家、搜索系统与买家的判断，避免无关商品干扰并维护卖家形象。由于难以收集负面反馈，大语言模型（LLM）被用作人类判断的可扩展代理。本文在主流电商平台上开展实证研究，提出一种蒸馏框架：以LLM为教师模型，交叉编码器为助手，基于嵌入的检索（EBR）模型为学生，旨在缓解点击诱导偏差，提升关键词推荐的相关性与多样性，同时对齐广告、搜索与买家偏好。
原文摘要 · Abstract (English)
E-commerce sellers are advised to bid on keyphrases to boost their advertising campaigns. These keyphrases must be relevant to prevent irrelevant items from cluttering Search systems and to maintain positive seller perception. It is vital that keyphrase suggestions align with seller, Search, and buyer judgments. Given the challenges in collecting negative feedback in these systems, LLMs have been used as a scalable proxy for human judgments. We present an empirical study on a major e-commerce platform of a distillation framework involving an LLM teacher, a cross-encoder assistant and a bi-encoder Embedding Based Retrieval (EBR) student model, aimed at mitigating click-induced biases and provide more diverse keyphrase recommendations while aligning advertising, search and buyer preferences.
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。