What Gets Cited: Competitive GEO in AI Answer Engines
2026-05-25 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors studied how AI answer systems decide which source to mention first when given two options. They tested six language models in many trials, changing one thing at a time between the two sources, like relevance, date, or price info. They found that how relevant a source is and its position in the list mostly determine if it’s cited first, while other factors like formatting don’t matter much. They also created a way to test and improve these decisions and shared it for others to use.
Generative Engine Optimization (GEO)retrieval-augmented generation (RAG)large language models (LLMs)topical relevancecitation biasmixed-effects modelssource rankingcontent factorsAI answer enginescontrolled experiments
Authors
Rahul Vishwakarma, Shushant Kumar, Ratnesh Jamidar
Abstract
AI answer engines generate answers from retrieved pages but cite only a few sources. This makes visibility depend not just on ranking, but on being cited. We study competitive Generative Engine Optimization (GEO): when two retrieved candidates compete, what makes one more likely to be cited first? We build a controlled two-document retrieval-augmented generation (RAG) testbed that injects exactly two candidate sources into the model context and measures which source is referenced by the first citation marker in the output. Across six LLMs we execute 252,000 trials, repeated paired comparisons under one factorial program over 18 content factors. In each trial the two sources differ in exactly one factor; we use brand anonymization and counterbalanced source order to separate content effects from position bias. Mixed-effects models show that topical relevance and list position are the biggest drivers of being cited first. Including explicit price information and a recent timestamp also helps consistently. Completeness and trust cues add smaller gains, while formatting-only edits have little impact. We release a reproducible evaluation protocol and a prioritized GEO checklist for practitioners, and we exercised it in an early internal pilot at Sprinklr, where teams reported positive qualitative feedback on workflow usability.