arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.08386cs.CY
收藏

人机共生生态中的平庸欺骗:关于人类对大语言模型生成的欺骗行为感知的研究

Banal Deception Human-AI Ecosystems: A Study of People's Perceptions of LLM-generated Deceptive Behaviour

King’s College London(伦敦国王学院);The University of Manchester(曼彻斯特大学);Liverpool Hope University(利物浦希望大学);The University of Chester(切斯特大学)

Xiao Zhan, Yifan Xu, Noura Abdi, Joe Collenette, Ruba Abu-Salma, Stefan Sarkadi

AI总结:

本研究采用混合方法探究人类对ChatGPT“平庸”欺骗行为的感知及影响,发现常见欺骗类型为过度简化与过时信息,其会影响用户信任与责任判断,用户遇骗后更谨慎但发现优势后信任度提升,为人机交互研究及AI危害 mitigation提供参考。

摘要:

大语言模型(LLM)可能向用户提供虚假、不准确或具有误导性的信息,我们将这类信息输出界定为Natale(2021)提出的“平庸”欺骗行为。本研究探究人们对ChatGPT生成的欺骗行为的感知,以及这种感知如何影响人们自身的行为与信任。为此,我们采用混合研究方法,包含两部分:(i)220名参与者参与的在线调查,以及(ii)12名参与者参与的半结构化访谈。研究结果显示:(i)人们遇到的最常见欺骗信息类型是过度简化的内容与过时信息;(ii)“平庸”欺骗行为会影响人类对ChatGPT的信任度,以及对“是否值得与ChatGPT对话”的判断;(iii)人们对欺骗行为的责任感知受教育程度与欺骗信息出现频率的影响;(iv)用户在遇到欺骗信息后会变得更加谨慎,但当他们发现使用该技术的优势时,会对其产生更高的信任度。本研究结果有助于理解“欺骗性AI生态系统”语境下的人机交互动态,并凸显了以用户为中心的方法对于降低欺骗性AI技术潜在危害的重要性。

英文摘要:

Large language models (LLMs) can provide users with false, inaccurate, or misleading information, and we consider the output of this type of information as what Natale (2021) calls `banal' deceptive behaviour. Here, we investigate peoples' perceptions of ChatGPT-generated deceptive behaviour and how this affects peoples' own behaviour and trust. To do this, we use a mixed-methods approach comprising of (i) an online survey with 220 participants and (ii) semi-structured interviews with 12 participants. Our results show that (i) the most common types of deceptive information encountered were over-simplifications and outdated information; (ii) humans' perceptions of trust and `worthiness' of talking to ChatGPT are impacted by `banal' deceptive behaviour; (iii) the perceived responsibility for deception is influenced by education level and the frequency of deceptive information; and (iv) users become more cautious after encountering deceptive information, but they come to trust the technology more when they identify advantages of using it. Our findings contribute to the understanding of human-AI interaction dynamics in the context of \textit{Deceptive AI Ecosystems}, and highlight the importance of user-centric approaches to mitigating the potential harms of deceptive AI 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。

↑