Answer Bubbles: Information Exposure in AI-Mediated Search

TL;DR

This study analyzes how AI-mediated search systems influence source diversity, language, and fidelity, revealing biases and the emergence of 'answer bubbles' that shape user perceptions of information.

Contribution

It provides a comprehensive comparison of four search systems, uncovering biases in source selection and the impact of AI summaries on information diversity and trust.

Findings

Generative systems show source-selection biases favoring certain sources.

Search integration reduces epistemic markers, decreasing hedging.

AI summaries overrepresent Wikipedia and long sources, underrepresent social media and negative sources.

Abstract

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.