Search papers, labs, and topics across Lattice.
This paper investigates how generative search systems (GPT, Search GPT, Google AI Overviews) differ from traditional search in source diversity, language, and fidelity to cited material by analyzing 11,000 real search queries. The study reveals that generative systems exhibit source-selection biases, selectively attenuate epistemic markers (reducing hedging), and compound citation biases, overrepresenting Wikipedia and longer sources while underrepresenting social media and negatively framed sources. These biases create "answer bubbles" where identical queries yield different information realities across systems.
Generative search engines create "answer bubbles" by selectively citing and framing information, leading to divergent information realities compared to traditional search.
Generative search systems are increasingly replacing link-based retrieval with AI-generated summaries, yet little is known about how these systems differ in sources, language, and fidelity to cited material. We examine responses to 11,000 real search queries across four systems -- vanilla GPT, Search GPT, Google AI Overviews, and traditional Google Search -- at three levels: source diversity, linguistic characterization of the generated summary, and source-summary fidelity. We find that generative search systems exhibit significant \textit{source-selection} biases in their citations, favoring certain sources over others. Incorporating search also selectively attenuates epistemic markers, reducing hedging by up to 60\% while preserving confidence language in the AI-generated summaries. At the same time, AI summaries further compound the citation biases: Wikipedia and longer sources are disproportionately overrepresented, whereas cited social media content and negatively framed sources are substantially underrepresented. Our findings highlight the potential for \textit{answer bubbles}, in which identical queries yield structurally different information realities across systems, with implications for user trust, source visibility, and the transparency of AI-mediated information access.
