Don't Measure Once: Measuring Visibility in AI Search (GEO)
Julius Schulte, Malte Bleeker, Philipp Kaufmann
TLDR
AI search visibility is probabilistic; this paper shows that repeated measurements are crucial for accurate Generative Engine Optimization (GEO) assessment.
Key contributions
- AI search results are probabilistic and vary across runs, prompts, and time.
- One-off observations are insufficient for reliable Generative Engine Optimization (GEO) assessment.
- Empirical studies demonstrate the necessity of repeated measurements for GEO performance.
- Visibility in AI search should be understood as a distribution, not a single-point outcome.
Why it matters
This paper addresses a critical challenge in Generative Engine Optimization (GEO). It reveals how the probabilistic nature of AI search fundamentally changes visibility measurement. This understanding is crucial for brands and info providers to develop effective strategies in the LLM era.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.