Answer Bubbles: Information Exposure in AI-Mediated Search

• URL: http://arxiv.org/abs/2603.16138v1
• Date: Tue, 17 Mar 2026 05:41:39 GMT
• Title: Answer Bubbles: Information Exposure in AI-Mediated Search
• Abstract summary: We examine responses to 11,000 real search queries across four systems -- vanilla GPT, Search GPT, Google AI Overviews, and traditional Google Search.<n>We find that generative search systems exhibit significant textitsource-selection biases in their citations.
• Score: 14.377773240202849
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• 'Your AI Text is not Mine': Redefining and Evaluating AI-generated Text Detection under Realistic Assumptions [50.1119556361129]
  We systematically define various notions of AI-generated text and their characteristics.<n>AITDNA is a new benchmark of human-machine co-constructed texts.<n>We benchmark various machine-generated text detectors and find that they often only perform well for specific notions but not as broad detectors.
  arXiv  Detail & Related papers  (2026-06-03T14:05:14Z)
• OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources [67.62754856088591]
  Existing retrievers operate over one source at a time under a fixed query language.<n>We present OmniRetrieval, a framework that takes any natural-language query and identifies appropriate knowledge sources.
  arXiv  Detail & Related papers  (2026-05-28T02:10:35Z)
• Synthetic Sources?: Auditing Generative Search Engine Citations for Evidence of AI-Generated Sources [3.2065257821139195]
  It is unclear whether generative search engines can reliably omit citing synthetic sources.<n>This work presents an audit of four generative search engines using a total of 712 real-world human-generated queries.<n>Our findings show evidence of AI-generated sources being cited across all four generative search engines.
  arXiv  Detail & Related papers  (2026-05-22T14:33:52Z)
• SemanticCite: Citation Verification with AI-Powered Full-Text Analysis and Evidence-Based Reasoning [0.0]
  We introduce SemanticCite, an AI-powered system that verifies citation accuracy through full-text source analysis.<n>Our approach combines multiple retrieval methods with a four-class classification system that captures nuanced claim-source relationships.<n>We contribute a comprehensive dataset of over 1,000 citations with detailed alignments, functional classifications, semantic annotations, and bibliometric metadata.
  arXiv  Detail & Related papers  (2025-11-20T10:05:21Z)
• Assessing Web Search Credibility and Response Groundedness in Chat Assistants [4.0127354590894955]
  We introduce a novel methodology for evaluating assistants' web search behavior.<n>Using 100 claims across five misinformation-prone topics, we assess GPT-4o, GPT-5, Perplexity, and Qwen Chat.
  arXiv  Detail & Related papers  (2025-10-15T16:55:47Z)
• VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification [107.75781898355562]
  We introduce a novel framework, called VeriCite, designed to rigorously validate supporting evidence and enhance answer attribution.<n>We conduct experiments across five open-source LLMs and four datasets, demonstrating that VeriCite can significantly improve citation quality while maintaining the correctness of the answers.
  arXiv  Detail & Related papers  (2025-10-13T13:38:54Z)
• News Source Citing Patterns in AI Search Systems [6.976269683687743]
  We analyze data from the AI Search Arena, a head-to-head evaluation platform for AI search systems.<n>The dataset comprises over 24,000 conversations and 65,000 responses from models across three major providers: OpenAI, Perplexity, and Google.<n>We find that while models from different providers cite distinct news sources, they exhibit shared patterns in citation behavior.
  arXiv  Detail & Related papers  (2025-07-07T02:17:57Z)
• Generative AI Search Engines as Arbiters of Public Knowledge: An Audit of Bias and Authority [2.860575804107195]
  This paper reports on an audit study of generative AI systems (ChatGPT, Bing Chat, and Perplexity) which investigates how these new search engines construct responses. We collected system responses using a set of 48 authentic queries for 4 topics over a 7-day period and analyzed the data using sentiment analysis, inductive coding and source classification. Results provide an overview of the nature of system responses across these systems and provide evidence of sentiment bias based on the queries and topics, and commercial and geographic bias in sources.
  arXiv  Detail & Related papers  (2024-05-22T22:09:32Z)
• DIVKNOWQA: Assessing the Reasoning Ability of LLMs via Open-Domain Question Answering over Knowledge Base and Text [73.68051228972024]
  Large Language Models (LLMs) have exhibited impressive generation capabilities, but they suffer from hallucinations when relying on their internal knowledge. Retrieval-augmented LLMs have emerged as a potential solution to ground LLMs in external knowledge.
  arXiv  Detail & Related papers  (2023-10-31T04:37:57Z)
• Large Language Models for Information Retrieval: A Survey [83.75872593741578]
  Information retrieval has evolved from term-based methods to its integration with advanced neural models.<n>Recent research has sought to leverage large language models (LLMs) to improve IR systems.<n>We delve into the confluence of LLMs and IR systems, including crucial aspects such as query rewriters, retrievers, rerankers, and readers.
  arXiv  Detail & Related papers  (2023-08-14T12:47:22Z)
• Evaluating Verifiability in Generative Search Engines [70.59477647085387]
  Generative search engines directly generate responses to user queries, along with in-line citations. We conduct human evaluation to audit four popular generative search engines. We find that responses from existing generative search engines are fluent and appear informative, but frequently contain unsupported statements and inaccurate citations.
  arXiv  Detail & Related papers  (2023-04-19T17:56:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.