Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.16138 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915869656875008 |
|---|---|
| author | Huang, Michelle Goyal, Agam Saha, Koustuv Chandrasekharan, Eshwar |
| author_facet | Huang, Michelle Goyal, Agam Saha, Koustuv Chandrasekharan, Eshwar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16138 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Answer Bubbles: Information Exposure in AI-Mediated Search Huang, Michelle Goyal, Agam Saha, Koustuv Chandrasekharan, Eshwar Information Retrieval Computation and Language 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. |
| title | Answer Bubbles: Information Exposure in AI-Mediated Search |
| topic | Information Retrieval Computation and Language |
| url | https://arxiv.org/abs/2603.16138 |