发表机构
Discovered Labs（Discovered Labs）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究基于两百万条商业LLM引用和一万个网页，发现提示-内容对齐是引用频率的主导预测因子，AEO清单效应在控制领域后反转，领域权威影响显著，并发布分析流程。
AI 中文摘要
生产级大语言模型在生成答案的同时会检索并引用网页，然而预测引用频率的页面级特征仍未得到充分刻画。我们开展了一项观察性研究，涵盖六个月期间来自四个商业引擎（ChatGPT、Claude、Google AI、Gemini）的约两百万条LLM引用，并将其与来自十九个B2B SaaS工作空间的一万个爬取页面进行关联。我们使用一个九方法共识框架测试了六十多个特征，该框架结合了混合效应回归与领域固定效应、FDR校正、稳定性选择Lasso、双重机器学习、广义加性模型以及时间保持复制。四项发现通过了所有检验。第一，提示-内容对齐（页面词元与完整工作空间提示语料库（包括非引用提示）之间的Jaccard重叠）是主导性的页面级预测因子（beta = +0.37，95%置信区间[+0.33，+0.41]，q ~ 10^-73）。第二，标准的AEO检查清单（FAQ块、结构化数据、Core Web Vitals）在合并数据中显示出正向效应，但在应用领域固定效应后这些效应反转或缩减为零：这是辛普森悖论，对AEO文献具有实际后果。第三，领域级AI权威度的平均绝对SHAP值比最强的非对齐页面级特征高出六倍。我们发布了分析流程作为方法论贡献。
英文摘要
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.
