arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.10258cs.HC
收藏

从可搜索到不可搜索:生成式AI与在线信息寻求中的信息多样性

From Searchable to Non-Searchable: Generative AI and Information Diversity in Online Information Seeking

Northwestern University(西北大学);University of Michigan(密歇根大学);Microsoft Research(微软研究院)

Yulin Yu, Yizhou Li, Tzu-Sheng Kuo, Kentaro Toyama, Siddharth Suri, Scott Counts

AI总结:

研究探讨生成式AI如何改变在线信息检索中的信息多样性,发现用户查询多为不可搜索内容,但AI响应在多数主题上多样性较低,揭示了AI输出与用户探索间的反馈循环。

摘要:

对话式生成式AI系统如ChatGPT正在改变人们在线获取和互动信息的方式。与传统搜索引擎不同,这些系统支持开放性和对话式查询,但尚不清楚它们最终是扩展还是限制了用户在在线搜索空间中遇到的知识多样性,这是知识工作、学习和创新的主要基础。利用超过20万次真实的人与ChatGPT交互数据,我们研究生成式AI介导的查询如何通过可搜索性(查询是否可能被传统搜索引擎回答)的视角重塑用户输入和系统输出中的多样性。我们发现几乎80%的ChatGPT用户查询不可搜索,涵盖更广的知识空间和主题,表明了扩展的查询模式。然而,对于可搜索查询,AI响应在多数主题上比谷歌搜索结果的多样性更低。此外,AI响应的多样性预测了用户后续查询多样性的变化,揭示了AI输出与人类探索间的反馈循环。这些发现突显了扩展查询与受限信息暴露之间的张力,对设计混合搜索和生成式AI系统以更好地支持探索性知识获取具有启示。

英文摘要:

Conversational generative AI systems such as ChatGPT are transforming how people seek and engage with information online. Unlike traditional search engines, these systems support open-ended, conversational inquiry, yet it remains unclear whether they ultimately expand or constrain the diversity of knowledge that users encounter in online search spaces, a primary foundation for knowledge work, learning, and innovation. Using over 200,000 real-world human-ChatGPT interactions, we examine how generative-AI-mediated inquiry reshapes diversity in both user inputs and system outputs through the lens of searchability - whether queries could plausibly be answered by traditional search engines. We find that almost 80% of ChatGPT user queries are non-searchable and span a broader knowledge space and topics than searchable queries, indicating expanded modes of inquiry. However, for comparable searchable queries, AI responses are less diverse than Google search results in the majority of topics. Moreover, the diversity of AI responses predicts subsequent changes in users' inquiry diversity, revealing a feedback loop between AI outputs and human exploration. These findings highlight a tension between expanded inquiry and constrained information exposure, with implications for designing hybrid search and generative-AI systems that better support exploratory knowledge seeking.

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。

↑