From Citation Selection to Citation Absorption: A Measurement Framework for Generative Engine Optimization Across AI Search Platforms

• URL: http://arxiv.org/abs/2604.25707v2
• Date: Wed, 29 Apr 2026 13:25:28 GMT
• Title: From Citation Selection to Citation Absorption: A Measurement Framework for Generative Engine Optimization Across AI Search Platforms
• Abstract summary: 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.
• Score: 0.1223474232275842
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative search engines increasingly determine whether online information is merely discoverable, cited as a source, or actually absorbed into generated answers. This paper proposes a two-stage measurement framework for Generative Engine Optimization (GEO): citation selection, where a platform triggers search and chooses sources, and citation absorption, where a cited page contributes language, evidence, structure, or factual support to the final answer. We analyze the public geo-citation-lab dataset covering 602 controlled prompts across ChatGPT, Google AI Overview/Gemini, and Perplexity; 21,143 valid search-layer citations; 23,745 citation-level feature records; 18,151 successfully fetched pages; and 72 extracted features. The central descriptive finding is that citation breadth and citation depth diverge. Perplexity and Google cite more sources on average, while ChatGPT cites fewer sources but shows substantially higher average citation influence among fetched pages. High-influence pages tend to be longer, more structured, semantically aligned, and richer in extractable evidence such as definitions, numerical facts, comparisons, and procedural steps. The results suggest that GEO should be measured beyond citation counts, with answer-level absorption treated as a separate outcome.

Related papers

• Explicit Evidence Grounding via Structured Inline Citation Generation [22.27784103991804]
  FullCite is a framework that generates structured inline citations linking each claim to both its source document and supporting evidence.<n>We assess citation quality and faithfulness along three dimensions: document-level correctness, evidence span identification, and claim-citation faithfulness.
  arXiv  Detail & Related papers  (2026-06-05T10:42:10Z)
• What Gets Cited: Competitive GEO in AI Answer Engines [0.866627581195388]
  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.
  arXiv  Detail & Related papers  (2026-05-25T07:20:08Z)
• CiteAudit: You Cited It, But Did You Read It? A Benchmark for Verifying Scientific References in the LLM Era [51.63024682584688]
  Large language models (LLMs) introduce a new risk: fabricated references that appear plausible but correspond to no real publications.<n>We present the first comprehensive benchmark and detection framework for hallucinated citations in scientific writing.<n>Our framework significantly outperforms prior methods in both accuracy and interpretability.
  arXiv  Detail & Related papers  (2026-02-26T19:17:39Z)
• AI Answer Engine Citation Behavior An Empirical Analysis of the GEO16 Framework [0.0]
  GEO-16 is a framework that converts on page quality signals into banded pillar scores and a normalized GEO score G that ranges from 0 to 1.<n>We collected 1,702 citations across three engines and audited 1,100 URLs.<n>In our corpus, the engines differed in the GEO quality of the pages they cited, and pillars related to Metadata and Freshness, Semantic HTML, and Structured Data showed the strongest associations with citation.
  arXiv  Detail & Related papers  (2025-09-13T00:29:32Z)
• SCIRGC: Multi-Granularity Citation Recommendation and Citation Sentence Preference Alignment [2.0383262889621867]
  We propose the SciRGC framework, which aims to automatically recommend citation articles and generate citation sentences for citation locations within articles.<n>The framework addresses two key challenges in academic citation generation: 1) how to accurately identify the author's citation intent and find relevant citation papers, and 2) how to generate high-quality citation sentences that align with human preferences.
  arXiv  Detail & Related papers  (2025-05-26T15:09:10Z)
• ALiiCE: Evaluating Positional Fine-grained Citation Generation [54.19617927314975]
  We propose ALiiCE, the first automatic evaluation framework for fine-grained citation generation. Our framework first parses the sentence claim into atomic claims via dependency analysis and then calculates citation quality at the atomic claim level. We evaluate the positional fine-grained citation generation performance of several Large Language Models on two long-form QA datasets.
  arXiv  Detail & Related papers  (2024-06-19T09:16:14Z)
• Evaluating Verifiability in Generative Search Engines [70.59477647085387]
  Generative search engines directly generate responses to user queries, along with in-line citations. We conduct human evaluation to audit four popular generative search engines. We find that responses from existing generative search engines are fluent and appear informative, but frequently contain unsupported statements and inaccurate citations.
  arXiv  Detail & Related papers  (2023-04-19T17:56:12Z)
• CiteBench: A benchmark for Scientific Citation Text Generation [69.37571393032026]
  CiteBench is a benchmark for citation text generation. We make the code for CiteBench publicly available at https://github.com/UKPLab/citebench.
  arXiv  Detail & Related papers  (2022-12-19T16:10:56Z)
• Controllable Citation Sentence Generation with Language Models [11.186252009101077]
  We propose to integrate the manuscript context, the context of the referenced paper, and the desired control attributes into a structured template and use it to fine-tune a language model (LM) via next-token prediction. The proposed workflow harmoniously combines citation attribute suggestion and conditional citation generation into one LM, allowing for better user control.
  arXiv  Detail & Related papers  (2022-11-14T01:54:08Z)
• Deep Graph Learning for Anomalous Citation Detection [55.81334139806342]
  We propose a novel deep graph learning model, namely GLAD (Graph Learning for Anomaly Detection), to identify anomalies in citation networks. Within the GLAD framework, we propose an algorithm called CPU (Citation PUrpose) to discover the purpose of citation based on citation texts.
  arXiv  Detail & Related papers  (2022-02-23T09:05:28Z)
• Towards generating citation sentences for multiple references with intent control [86.53829532976303]
  We build a novel generation model with the Fusion-in-Decoder approach to cope with multiple long inputs. Experiments demonstrate that the proposed approaches provide much more comprehensive features for generating citation sentences.
  arXiv  Detail & Related papers  (2021-12-02T15:32:24Z)
• Virtual Proximity Citation (VCP): A Supervised Deep Learning Method to Relate Uncited Papers On Grounds of Citation Proximity [0.0]
  This paper discusses the approach Virtual Citation Proximity (VCP) The actual distance between the two citations in a document is used as ground truth. This can be used to calculate relatedness between two documents in a way they would have been cited in the proximity even if the documents are uncited.
  arXiv  Detail & Related papers  (2020-09-25T12:24:00Z)

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.