mlsanityData to 14 Oct 2026

Measuring GEO Visibility: Prompt Corpora Define the Answer Market

arXiv 2609.06811 ↗First posted 6 Sep 2026cs.IR cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

GEO (generative engine optimization) visibility scores aggregate source appearances, citations, or brand mentions in generated answers. The prompt corpus selects the situations evaluated, while weights determine their relative importance. Together they define an "answer market" that need not represent actual user demand. Prompt wording can alter retrieval, competing sources, and generated answers. Scoring then requires identifying the appearances, citations, or mentions of interest. If a language model performs this task, its instruction can change the score assigned to an unchanged answer. Our critical survey examines how these choices help define what a GEO score measures. It draws on research into whether indicators measure the intended phenomenon, total survey error, and information retrieval evaluation. The framework specifies situation annotation, prompt formulations, execution conditions, weights, and scoring rules. When weights are unknown or remain to be chosen, the framework reports sets of admissible scores. It distinguishes values compatible with data and assumptions about a target population (partial identification) from variation across weighting conventions (normative sensitivity). A citation alone does not establish a source's contribution. The article defines a comparison of answers generated with and without a source in a controlled documentary context, distinct from an intervention on the full engine with competing sources. The framework is supported by reproducible calculations. No new experiments are reported; its general empirical validity remains to be assessed.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 44 references that are in the map. First posted on arXiv 6 Sep 2026.

Builds on

27 of 44 references.

References · 27

  1. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  2. 2018Datasheets for Datasetscited by 1,386
  3. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
  4. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  5. 2024WildChat: 1M ChatGPT Interaction Logs in the Wildcited by 629
  6. 2023Enabling Large Language Models to Generate Text with Citationscited by 595
  7. 2023LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Datasetcited by 461
  8. 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
  9. 2021AI and the Everything in the Whole Wide World Benchmarkcited by 349
  10. 2023State of What Art? A Call for Multi-Prompt LLM Evaluationcited by 310
  11. 2024tinyBenchmarks: evaluating LLMs with fewer examplescited by 310
  12. 2019Measurement and Fairnesscited by 308
15 more
  1. 2021Measuring Attribution in Natural Language Generation Modelscited by 256
  2. 2021What Will it Take to Fix Benchmarking in Natural Language Understanding?cited by 203
  3. 2024Efficient multi-prompt evaluation of LLMscited by 73
  4. 2023GEO: Generative Engine Optimizationcited by 56
  5. 2025Search Arena: Analyzing Search-Augmented LLMscited by 34
  6. 2025Flaw or Artifact? Rethinking Prompt Sensitivity in Evaluating LLMscited by 30
  7. 2025ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of Momentscited by 11
  8. 2025Beyond the Singular: Revealing the Value of Multiple Generations in Benchmark Evaluationcited by 5
  9. 2026SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimizationcited by 5
  10. 2026The Discovery Gap: How Product Hunt Startups Vanish in LLM Organic Discovery Queriescited by 2
  11. 2026How Generative AI Disrupts Search: An Empirical Study of Google Search, Gemini, and AI Overviewscited by 2
  12. 2026Paraphrase Brittleness in Production Retrieval-Augmented Commercial Recommendation: Reproducibility Below the Rerun-Stability Baselinecited by 2
  13. 2026Measuring Google AI Overviews: Activation, Source Quality, Claim Fidelity, and Publisher Impactcited by 1
  14. 2026Demand-Side Measurement for Generative Engine Optimization: Constructing and Validating a Million-Persona, Intent-Annotated Buyer Corpuscited by 1
  15. 2026The Language of the Question Selects the Market: Query Language and Exit IP as Separable Factors in Commercial Recommendations from a Generative Search Interfacecited by 1

Built on by

Not cited yet.