# What Drives Citations in Production Large Language Models? An Observational Multi-Method Study of Two Million AI Citations Across Ten Thousand Web Pages

arXiv: https://arxiv.org/abs/2609.35077 · HTML: https://mlsanity.com/paper/2609.35077/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 15 of 15)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Evaluating Verifiability in Generative Search Engines](https://mlsanity.com/paper/2304.09848/) (2023)
- [RARR: Researching and Revising What Language Models Say, Using Language Models](https://mlsanity.com/paper/2210.08726/) (2022)
- [How is ChatGPT's behavior changing over time?](https://mlsanity.com/paper/2307.09009/) (2023)
- [How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility](https://mlsanity.com/paper/1710.11214/) (2017)
- [Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models](https://mlsanity.com/paper/2212.08037/) (2022)
- [GEO: Generative Engine Optimization](https://mlsanity.com/paper/2311.09735/) (2023)
- [Manipulating Large Language Models to Increase Product Visibility](https://mlsanity.com/paper/2404.07981/) (2024)
- [News Source Citing Patterns in AI Search Systems](https://mlsanity.com/paper/2507.05301/) (2025)
- [Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines](https://mlsanity.com/paper/2512.09483/) (2025)
- [Structural Feature Engineering for Generative Engine Optimization: How Content Structure Shapes Citation Behavior](https://mlsanity.com/paper/2603.29979/) (2026)
- [From Citation Selection to Citation Absorption: A Measurement Framework for Generative Engine Optimization Across AI Search Platforms](https://mlsanity.com/paper/2604.25707/) (2026)

## Abstract (arXiv)

Production large language models retrieve and cite web pages alongside generated answers, yet the page-level features that predict citation frequency remain poorly characterised. We present an observational study of approximately 2 million LLM citations from four commercial engines (ChatGPT, Claude, Google AI, Gemini) over six months, joined to 10,000 crawled pages from nineteen B2B SaaS workspaces. Sixty-plus features are tested using a nine-method consensus framework combining mixed-effects regression with domain fixed effects, FDR correction, stability-selection Lasso, double machine learning, generalised additive models, and temporal hold-out replication. Four findings survive all checks. First, prompt-content alignment (Jaccard overlap between page tokens and the full workspace prompt corpus, including non-citing prompts) is the dominant page-level predictor (beta = +0.37, 95% CI [+0.33, +0.41], q ~ 10^-73). Second, the standard AEO checklist (FAQ blocks, structured data, Core Web Vitals) shows positive effects in pooled data that reverse or collapse to zero once domain fixed effects are applied: Simpson's paradox with practical consequences for the AEO literature. Third, domain-level AI authority exceeds the strongest non-alignment page-level feature by a factor of six in mean absolute SHAP value. We release the analytic pipeline as a methodological contribution.