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 2602.01114cs.HCcs.CY
收藏

用ChatGPT打乒乓球:关于与对话式AI系统互动的演变

Bowling with ChatGPT: On the Evolving User Interactions with Conversational AI Systems

Indian Institute of Technology Kharagpur(印度理工学院卡拉格普尔分校);Max Planck Institute for Software Systems(马克斯·普朗克软件系统研究所);Saarland University(萨尔兰大学);Delft University of Technology(代尔夫特理工大学)

Sai Keerthana Karnam, Abhisek Dash, Krishna P. Gummadi, Animesh Mukherjee, Ingmar Weber, Savvas Zannettou

AI总结:

研究发现,用户与ChatGPT的互动逐渐从功能性工具转向社交伙伴,互动目的扩大,系统拟人化增加,引导动态显著增强。

摘要:

最近的研究讨论了用户越来越多地使用由LLM驱动的对话式AI系统进行信息检索、决策支持,甚至情感支持。然而,这些宏观层面的观察对互动目的如何随时间变化、用户如何框定与系统的互动,以及这些人机互动中的引导动态如何演变提供了有限的洞察。为了研究这些演变动态,我们收集并分析了一个独特的数据集InVivoGPT:由300名用户通过GDPR数据权利捐赠的825,000次ChatGPT互动。我们的分析揭示了三个关键发现。首先,参与者越来越倾向于将ChatGPT用于更广泛的目的,包括在健康和心理健康等敏感领域显著增长。第二,互动变得更加社会化:系统自我拟人化的比例上升,参与者更频繁地将其视为伴侣,个人数据披露变得既更常见又更多样。第三,对话引导变得更加突出,尤其是在GPT-4o发布后,参与者遵循模型建议的对话数量在我们的数据集期间增加了四倍。总体而言,我们的结果表明,对话式AI系统正从功能性工具转变为社交伙伴,提出了关于其设计和治理的重要问题。

英文摘要:

Recent studies have discussed how users are increasingly using conversational AI systems, powered by LLMs, for information seeking, decision support, and even emotional support. However, these macro-level observations offer limited insight into how the purpose of these interactions shifts over time, how users frame their interactions with the system, and how steering dynamics unfold in these human-AI interactions. To examine these evolving dynamics, we gathered and analyzed a unique dataset InVivoGPT: consisting of 825K ChatGPT interactions, donated by 300 users through their GDPR data rights. Our analyses reveal three key findings. First, participants increasingly turn to ChatGPT for a broader range of purposes, including substantial growth in sensitive domains such as health and mental health. Second, interactions become more socially framed: the system anthropomorphizes itself at rising rates, participants more frequently treat it as a companion, and personal data disclosure becomes both more common and more diverse. Third, conversational steering becomes more prominent, especially after the release of GPT-4o, with conversations where the participants followed a model-initiated suggestion quadrupling over the period of our dataset. Overall, our results show that conversational AI systems are shifting from functional tools to social partners, raising important questions about their design and governance.

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。

↑