A new paper on arXiv explores the concept of "generative engine optimization" (GEO) visibility scores, which aggregate source appearances, citations, or brand mentions in AI-generated answers. The research highlights that the prompt corpus and weighting systems used to define these scores create an "answer market" that may not reflect actual user demand. The paper proposes a framework for analyzing how prompt wording, scoring identification, and language model instructions can influence these scores, distinguishing between values compatible with data and variations across weighting conventions. AI
IMPACT This research provides a framework for understanding and evaluating how AI systems are perceived and ranked, impacting the development of more transparent and user-aligned generative models.
RANK_REASON The cluster contains a research paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]
Read on arXiv cs.IR (Information Retrieval) →
- alphaXiv
- arXiv
- CatalyzeX
- Connected Papers
- DagsHub
- generative engine optimization
- Gotit.pub
- Hugging Face
- Influence Flower
- Litmaps
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →