What Gets Cited: Competitive GEO in AI Answer Engines

• URL: http://arxiv.org/abs/2605.25517v1
• Date: Mon, 25 May 2026 07:20:08 GMT
• Title: What Gets Cited: Competitive GEO in AI Answer Engines
• Abstract summary: When two retrieved candidates compete, what makes one more likely to be cited first?<n>We build a controlled two-document retrieval-augmented generation testbed that injects exactly two candidate sources into the model context.<n>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.
• Score: 0.866627581195388
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Measuring GEO Visibility: Prompt Corpora Define the Answer Market [0.0]
  GEO (generative engine optimization) visibility scores aggregate source appearances, citations, or brand mentions in generated answers.<n>The framework specifies situation annotation, prompt formulations, execution conditions, weights, and scoring rules.<n>The article defines a comparison of answers generated with and without a source in a controlled documentary context.
  arXiv  Detail & Related papers  (2026-09-06T20:07:53Z)
• Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research [75.8770212601511]
  Deep research (DR) systems produce long-form cited reports by orchestrating multiple agents that search and synthesize information from the web.<n> Citations are the primary mechanism for evaluating the faithfulness of these reports, yet current DR systems exhibit poor citation recall.<n>We propose an evaluation method that pinpoints which agent introduced each error by locally testing agent invocations for faithfulness and verifiability relative to their own inputs.
  arXiv  Detail & Related papers  (2026-08-25T09:34:18Z)
• Optimizing Visibility in Generative Engines: A Critical Survey of Generative Engine Optimization (2023-2026) [0.0]
  Generative Engine Optimization seeks to increase content's presence, likelihood of citation, or influence in answers produced by generative engines.<n>This critical survey reviews 45 studies selected under a November 2023-July 2026 publication window.
  arXiv  Detail & Related papers  (2026-07-15T17:03:08Z)
• How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented Generation [3.4562767039451674]
  We show how a large language model decides whether to attach an inline citation while answering a factoid question.<n>We show that amplifying or attenuating only those critical heads and eliminating 69% of spurious ones on PopQA without harming answer accuracy.<n>The results reveal a potential disconnect between the model's apparent reasoning and its internal computational pathway.
  arXiv  Detail & Related papers  (2026-06-09T07:06:13Z)
• Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding [64.98167175790817]
  We propose ConSUM that reranks candidate summaries by considering two factors: consistency to the source document and consensus among the other candidates.<n>Our system is competitive with existing methods, with human evaluations confirming that its generated summaries are preferred over those from other systems.
  arXiv  Detail & Related papers  (2026-05-28T04:14:43Z)
• From Citation Selection to Citation Absorption: A Measurement Framework for Generative Engine Optimization Across AI Search Platforms [0.1223474232275842]
  This paper proposes a two-stage measurement framework for Generative Engine Optimization (GEO)<n>We analyze the public geo-citation-lab dataset covering 602 controlled prompts across ChatGPT, Google AI Overview/Gemini, and Perplexity.<n>Perplexity and Google cite more sources on average, while ChatGPT cites fewer sources but shows substantially higher average citation influence among fetched pages.
  arXiv  Detail & Related papers  (2026-04-28T14:34:20Z)
• CRISP: Characterizing Relative Impact of Scholarly Publications [70.25915589244961]
  We propose CRISP, which jointly ranks all cited papers within a citing paper using large language models (LLMs)<n>To mitigate LLMs' positional bias, we rank each list three times in a randomized order and aggregate the impact labels through majority voting.<n>CRISP outperforms a prior state-of-the-art impact classifier by +9.5% accuracy and +8.3% F1 on a dataset of human-annotated citations.
  arXiv  Detail & Related papers  (2026-03-25T16:42:30Z)
• VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification [107.75781898355562]
  We introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution.<n>We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.
  arXiv  Detail & Related papers  (2025-10-13T13:38:54Z)
• Generation-Time vs. Post-hoc Citation: A Holistic Evaluation of LLM Attribution [8.691344810384114]
  Large Language Models (LLMs) must cite human-verifiable sources in high-stakes domains such as healthcare, law, academia, and finance.<n>We introduce two paradigms: Generation-Time Citation (G-Cite) which produces the answer and citations in one pass, and Post-hoc Citation (P-Cite) which adds or verifies citations after drafting.<n>Our results show a consistent trade-off between coverage and citation correctness, with retrieval as the main driver of attribution quality in both paradigms.
  arXiv  Detail & Related papers  (2025-09-25T20:39:26Z)
• List-aware Reranking-Truncation Joint Model for Search and Retrieval-augmented Generation [80.12531449946655]
  We propose a Reranking-Truncation joint model (GenRT) that can perform the two tasks concurrently. GenRT integrates reranking and truncation via generative paradigm based on encoder-decoder architecture. Our method achieves SOTA performance on both reranking and truncation tasks for web search and retrieval-augmented LLMs.
  arXiv  Detail & Related papers  (2024-02-05T06:52:53Z)
• CausalCite: A Causal Formulation of Paper Citations [80.82622421055734]
  CausalCite is a new way to measure the significance of a paper by assessing the causal impact of the paper on its follow-up papers. It is based on a novel causal inference method, TextMatch, which adapts the traditional matching framework to high-dimensional text embeddings. We demonstrate the effectiveness of CausalCite on various criteria, such as high correlation with paper impact as reported by scientific experts.
  arXiv  Detail & Related papers  (2023-11-05T23:09:39Z)
• Large Language Models are not Fair Evaluators [60.27164804083752]
  We find that the quality ranking of candidate responses can be easily hacked by altering their order of appearance in the context. This manipulation allows us to skew the evaluation result, making one model appear considerably superior to the other. We propose a framework with three simple yet effective strategies to mitigate this issue.
  arXiv  Detail & Related papers  (2023-05-29T07:41:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.