When Content is Goliath and Algorithm is David: The Style and Semantic Effects of Generative Search Engine

Authors: L Ma, J Qin, X Xu, Y Tan

Published: 2025

Publication: arXiv preprint arXiv:2509.14436, 2025•arxiv.org

This paper studies how generative search engines that use large language models (LLMs)—like Google’s AI overviews—select and cite web content, showing that these engines prefer content that is more predictable and semantically coherent for the model, and that LLM-based content polishing can increase the diversity and usefulness of AI summaries for users.

Institution: University of North Carolina Charlotte, University of Science and Technology of China, University of Washington

Research Area: LLM behavior, Algorithmic content preference, Human–AI interaction

Discipline: Computer Science, Information Retrieval, Artificial Intelligence

DOI: https://doi.org/10.48550/arXiv.2509.14436