# What Gets Cited: Competitive GEO in AI Answer Engines

arXiv: https://arxiv.org/abs/2605.25517 · HTML: https://mlsanity.com/paper/2605.25517/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 25 May 2026.

## Builds on (most cited first, 6 of 6)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [GEO: Generative Engine Optimization](https://mlsanity.com/paper/2311.09735/) (2023)
- ["Global is Good, Local is Bad?": Understanding Brand Bias in LLMs](https://mlsanity.com/paper/2406.13997/) (2024)
- [Dense Passage Retrieval: Is it Retrieving?](https://mlsanity.com/paper/2402.11035/) (2024)

## Built on by (most cited first, 2 of 2)

- [Who Gets Named: Citation Type Predicts Individual Naming by Grounded Language Models, and a Roster Instrument Captures 0.5% of It](https://mlsanity.com/paper/2607.23893/) (2026)
- [CITECHOICE: A Causal Audit of How Document Presentation Redistributes Citation Credit in Agentic Search](https://mlsanity.com/paper/2609.15164/) (2026)

## Abstract (arXiv)

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.