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 2601.09898cs.HC
收藏

在人机信息检索对话中烹饪礼貌

Cooking Up Politeness in Human-AI Information Seeking Dialogue

University of Regensburg(雷根斯堡大学);University of Innsbruck(因斯布鲁克大学)

David Elsweiler, Christine Elsweiler, Anna Ziegner

AI总结:

研究探讨了礼貌行为在人机信息检索对话中的影响,发现礼貌显著影响响应长度、信息增益和效率,且礼貌请求可能隐含更高的能耗。

摘要:

礼貌是人类交流的核心维度,但其在人机信息检索中的作用仍处于探索阶段。我们研究了用户礼貌行为如何在烹饪协助场景中影响对话结果。首先,我们标注了30个对话,识别出四个不同的用户群体,从极度礼貌到极度高效。然后我们扩展到18000次模拟对话,覆盖五个礼貌类型(包括不礼貌)和三个开放式模型。结果显示,礼貌不仅是一种装饰:它系统地影响响应长度、信息增益和效率。寻求参与的提示生成的回复比超高效提示长90%,并包含38%更多信息点,但密度明显较低。不礼貌的输入产生了冗长但效率较低的回答,每瓦时的信息点比礼貌输入少48%。这些发现突显了礼貌作为公平和可持续性问题:对话风格可能使用户受益或受损,而“礼貌”的请求可能隐含着隐藏的能量成本。我们讨论了包容性和资源敏感性信息代理设计的含义。

英文摘要:

Politeness is a core dimension of human communication, yet its role in human-AI information seeking remains underexplored. We investigate how user politeness behaviour shapes conversational outcomes in a cooking-assistance setting. First, we annotated 30 dialogues, identifying four distinct user clusters ranging from Hyperpolite to Hyperefficient. We then scaled up to 18,000 simulated conversations across five politeness profiles (including impolite) and three open-weight models. Results show that politeness is not only cosmetic: it systematically affects response length, informational gain, and efficiency. Engagement-seeking prompts produced up to 90% longer replies and 38% more information nuggets than hyper-efficient prompts, but at markedly lower density. Impolite inputs yielded verbose but less efficient answers, with up to 48% fewer nuggets per watt-hour compared to polite input. These findings highlight politeness as both a fairness and sustainability issue: conversational styles can advantage or disadvantage users, and "polite" requests may carry hidden energy costs. We discuss implications for inclusive and resource-aware design of information agents.

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。

↑