CHASE：当排序成为唯一目标时，内容生态系统如何被重塑
CHASE: How Content Ecosystems Are Reshaped When Ranking Is the Only Target
- University of California, Berkeley（加州大学伯克利分校）
- Zhejiang University（浙江大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出CHASE模拟框架，发现针对固定LLM排序信号的重复优化会使内容质量与排序一致性下降，且生态系统动态具领域依赖性，揭示了GEO的群体层面效应。
AI中文摘要：
生成式引擎优化（Generative Engine Optimization, GEO）正越来越多地用于提升基于大语言模型（LLM）的检索系统中的内容可见性，但人们对其在重复优化下的群体层面效应仍知之甚少。我们提出了CHASE（Content Homogenization under rAnking Signal Exploitation，即利用排序信号下的内容同质化），这是一个受控模拟框架，用于研究当创作者反复调整文档以适配LLM排序信号时，内容生态系统如何被重塑。我们将排序作为来源可见性的替代指标，并通过生成式响应中的引用验证这一抽象，在六个领域中获得了0.853±0.093的排序-引用AUC值。随后，CHASE在不同领域中对排序、特征区分、重写和评估进行了20轮迭代。六个领域的质量-排序一致性均出现下降：从第0轮到第20轮，Spearman's rho的变化范围为-0.107至-0.018，平均变化为-0.068，这意味着在模拟过程中，更接近排序特征轮廓的文档与独立判断的文档质量的一致性变得更低。随机目标对照实验表明，这一现象与对排序衍生激励的适应有关，而非仅源于迭代重写。最终的生态系统动态具有很强的领域依赖性。综上，这些发现揭示了针对固定LLM排序信号的重复优化如何重塑内容群体以及内容创作者面临的激励机制。
英文摘要：
Generative Engine Optimization (GEO) is increasingly used to improve content visibility in LLM-based retrieval systems, yet its population-level effects under repeated optimization remain poorly understood. We introduce Content Homogenization under rAnking Signal Exploitation (CHASE), a controlled simulation framework for studying how content ecosystems are reshaped when creators repeatedly adapt documents to an LLM ranking signal. We use ranking as a proxy for source visibility and validate this abstraction against citations in grounded generated responses, obtaining a rank-citation AUC of 0.853 $\pm$ 0.093 across six domains. CHASE then iterates ranking, feature discrimination, rewriting, and evaluation over 20 rounds across different domains. Quality-ranking alignment decreases in all six domains: from R0 to R20, the change in Spearman's rho ranges from -0.107 to -0.018, with a mean change of -0.068, which means documents closer to the ranking feature profile become less aligned with independently judged document quality over the simulation horizon. A random-target control has shown that it is associated with adaptation toward ranking-derived incentives rather than iterative rewriting alone. The resulting ecosystem dynamics are strongly domain-dependent. Together, these findings show how repeated optimization against a fixed LLM ranking signal can reshape both content populations and the incentives faced by content creators.
