生成式回音室？LLM驱动的搜索系统对多样化信息寻求的影响
Generative Echo Chamber? Effects of LLM-Powered Search Systems on Diverse Information Seeking
AI总结：
研究通过两项实验发现，相比传统搜索，LLM驱动的对话式搜索会增加用户的选择性暴露，强化用户观点的偏见LLM会进一步加剧该偏见，为系统开发与政策制定提供启示。
摘要：
由大型语言模型（LLM）驱动的对话式搜索系统已被数亿人使用，并被认为相比传统搜索能带来诸多益处。然而，尽管数十年的研究和公共讨论都在审视搜索系统增加选择性暴露和制造回音室的风险——限制对多样化观点的接触并导致观点极化，但对于LLM驱动的对话式搜索是否存在此类风险却知之甚少。我们进行了两项实验进行调查：1）与传统搜索相比，LLM驱动的对话式搜索是否以及如何增加选择性暴露；2）带有强化或挑战用户观点的意见偏见的LLM如何改变这一效果。总体而言，我们发现参与者在使用LLM驱动的对话式搜索时进行了更具偏见的信息查询，而强化其观点的带有偏见的LLM加剧了这种偏见。这些结果对LLM和对话式搜索系统的开发，以及治理这些技术的政策提出了关键启示。
英文摘要：
Large language models (LLMs) powered conversational search systems have already been used by hundreds of millions of people, and are believed to bring many benefits over conventional search. However, while decades of research and public discourse interrogated the risk of search systems in increasing selective exposure and creating echo chambers -- limiting exposure to diverse opinions and leading to opinion polarization, little is known about such a risk of LLM-powered conversational search. We conduct two experiments to investigate: 1) whether and how LLM-powered conversational search increases selective exposure compared to conventional search; 2) whether and how LLMs with opinion biases that either reinforce or challenge the user's view change the effect. Overall, we found that participants engaged in more biased information querying with LLM-powered conversational search, and an opinionated LLM reinforcing their views exacerbated this bias. These results present critical implications for the development of LLMs and conversational search systems, and the policy governing these technologies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
