返回全部动态

位置决定生成:生成式引擎优化中提问地点的影响

原标题:Location, Location, Generation: Where You Ask Matters for Generative Engine Optimization

arXiv cs.IR一手来源研究质量 76

AI 摘要

该论文对生成式搜索引擎如何根据用户位置改变引用来源进行了受控审计。研究者向ChatGPT(19个声明位置)和ChatGPT、Gemini(5个网络位置)发送300个问题,共获得31,200条回答。结果显示ChatGPT遵循应用声明的位置(精确到城市),而Gemini忽略声明位置、跟随网络所在国家,且推荐商家随来源变化。这表明生成式搜索的可见性具有位置特异性,GEO监测必须同时控制声明位置和网络位置两个渠道。

以上摘要由 AI 生成,可能存在误差。事实请以原文为准。

正文节选

Location, Location, Generation: Where You Ask Matters for Generative Engine Optimization Abstract. Generative search engines answer local and commercial questions with a written answer and a few cited sources. A growing practice of generative engine optimization (GEO) monitors which sources and brands these answers show, typically from a single place. In this paper, we present a controlled audit of how the user’s location changes the sources that generative engines cite. We ask 300 questions of


发布时间:2026-10-20 12:00
抓取时间:2026-10-20 12:55
来源机构:arXiv
阅读原文arxiv.org