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 2103.05434cs.CYcs.AI
收藏

什么时候允许人工智能撒谎?基于信任的方法

When is it permissible for artificial intelligence to lie? A trust-based approach

Carnegie Mellon University(卡内基梅隆大学)

Tae Wan Kim, Tong, Lu, Kyusong Lee, Zhaoqi Cheng, Yanhan Tang, John Hooker

摘要:

在工业环境中使用的会话式人工智能(AI)可以被训练成密切模仿人类行为,包括撒谎和欺骗。然而,撒谎往往是谈判的必要组成部分。为了解决这个问题,我们开发了一个规范性框架,根据在特定场景中是否存在我们所说的“信任邀请”,判断对话式人工智能对人类撒谎是道德的还是不道德的。重要的是,文化规范在确定谈判环境中是否存在信任邀请方面发挥着重要作用,因此在一种文化中训练的人工智能可能无法推广到其他文化。此外,个人可能对人类与人工智能谈判者的信任邀请和撒谎倾向有不同的期望,这些期望也可能因文化而异。最后,我们概述了如何通过将自回归模型应用于大型对话和谈判数据集来训练会话聊天机器人进行道德谈判。

英文摘要:

Conversational Artificial Intelligence (AI) used in industry settings can be trained to closely mimic human behaviors, including lying and deception. However, lying is often a necessary part of negotiation. To address this, we develop a normative framework for when it is ethical or unethical for a conversational AI to lie to humans, based on whether there is what we call "invitation of trust" in a particular scenario. Importantly, cultural norms play an important role in determining whether there is invitation of trust across negotiation settings, and thus an AI trained in one culture may not be generalizable to others. Moreover, individuals may have different expectations regarding the invitation of trust and propensity to lie for human vs. AI negotiators, and these expectations may vary across cultures as well. Finally, we outline how a conversational chatbot can be trained to negotiate ethically by applying autoregressive models to large dialog and negotiations datasets.

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。

↑