对比五种生成式搜索系统，发现信息呈现存在显著偏差。
Answer Bubbles: Information Exposure in AI-Mediated Search
- 分析11000个真实查询，比较五类系统的来源选择与摘要语言特征。
- 生成摘要中疑虑表达减少60%，维基百科等长文被过度引用。
- 揭示'答案气泡'现象，适合关注AI信息透明度的研究者阅读。
生成式搜索系统正逐步取代基于链接的检索，转向由AI生成的摘要，但关于这些系统在信息来源、语言风格及对引用材料忠实度方面的差异仍知之甚少。我们针对11000个真实搜索查询，在五种系统——普通GPT、Search GPT、Perplexity Search with Grok、Google AI Overviews以及传统Google Search——上进行了多层级分析：包括来源多样性、生成摘要的语言特征，以及来源与摘要的一致性。研究发现，生成式搜索系统存在显著的源选择偏倚，倾向于优先引用特定来源。引入搜索功能后，认知标记（如疑虑表达）被选择性削弱，疑虑语气最高降低60%，而自信表述则得以保留。同时，AI摘要进一步加剧了引用偏倚：维基百科和较长文档被过度代表，而社交媒体内容及负面表述来源则被显著低估。研究揭示了‘答案气泡’现象，即相同查询在不同系统中生成的信息现实结构迥异，对用户信任、来源可见性及AI中介信息获取的透明度带来深远影响。
原文摘要 · Abstract (English)
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 five systems---vanilla GPT, Search GPT, Perplexity Search with Grok, 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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。