arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.07585cs.IRcs.AI
收藏

不要一次测量:AI搜索中的可见性测量(GEO)

Don't Measure Once: Measuring Visibility in AI Search (GEO)

Aurora Intelligence

Julius Schulte, Malte Bleeker, Philipp Kaufmann

AI总结:

研究探讨了AI搜索中可见性测量的必要性,指出单次测量不可靠,需多次测量以评估品牌GEO表现及可视化分布。

摘要:

随着基于大型语言模型的聊天系统日益普及,生成引擎优化(GEO)已成为信息获取和检索的重要问题。在经典搜索引擎中,结果相对透明且稳定:单次查询通常能提供页面或品牌相对于竞争对手的代表性快照。AI搜索的内在概率性质改变了这一范式。答案可能因运行、提示和时间而异,使单次观察不可靠。基于实证研究,我们的发现强调了需要重复测量以评估品牌GEO表现,并将可见性视为分布而非单一结果。

英文摘要:

As large language model-based chat systems become increasingly widely used, generative engine optimization (GEO) has emerged as an important problem for information access and retrieval. In classical search engines, results are comparatively transparent and stable: a single query often provides a representative snapshot of where a page or brand appears relative to competitors. The inherent probabilistic nature of AI search changes this paradigm. Answers can vary across runs, prompts, and time, making one-off observations unreliable. Drawing on empirical studies, our findings underscore the need for repeated measurements to assess a brand's GEO performance and to characterize visibility as a distribution rather than a single-point outcome.

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。

↑