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 2604.06183cs.HC
收藏

响应延迟和任务类型对人与大语言模型交互与感知的影响

The Impact of Response Latency and Task Type on Human-LLM Interaction and Perception

New York University(纽约大学);National University of Singapore(新加坡国立大学)

Felicia Fang-Yi Tan, Moritz A. Messerschmidt, Wen Yin, Oded Nov

AI总结:

研究探讨了响应延迟和任务类型对人与LLM交互行为及感知的影响,发现任务类型影响用户提示频率,延迟时间影响输出评价,提出延迟是可调节的设计变量。

摘要:

在大型语言模型(LLM)应用中,响应速度被广泛认为是关键因素,但延迟对用户行为和输出质量感知的影响尚未系统研究。本文通过控制实验,改变时间到第一个标记的延迟(2、9、20秒)在两种知识任务类型(创造和建议)中,发现用户交互行为对延迟具有鲁棒性,但因任务类型而异:创造任务引发更频繁的提示。相比之下,经历2秒延迟的参与者认为LLM输出不够思考和有用,而9-20秒延迟的参与者则有更高的评价。参与者将延迟归因于AI的思考,但长时间等待有时会改变这种解释为沮丧或对可靠性担忧。总体而言,这项工作表明延迟不仅是成本,而是具有伦理影响的可调节设计变量,提供了增强人与LLM交互的设计策略。

英文摘要:

Responsiveness in large language model (LLM) applications is widely assumed to be critical, yet the impact of latency on user behavior and perception of output quality has not been systematically explored. We report a controlled experiment varying time-to-first-token latency (2, 9, 20 seconds) across two taxonomy-driven knowledge task types (Creation and Advice). Log analyses reveal that user interaction behaviors were robust to latency, yet varied by task type: Creation tasks elicited more frequent prompting than Advice tasks. In contrast, participants who experienced 2-second latencies rated the LLM's outputs less thoughtful and useful than those who experienced 9- or 20-second latencies. Participants attributed delays to AI deliberation, though long waits occasionally shifted this interpretation toward frustration or concerns about reliability. Overall, this work demonstrates that latency is not simply a cost to reduce but a tunable design variable with ethical implications. We offer design strategies for enhancing human-LLM interaction.

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。

↑