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 2110.07574cs.CL
收藏

机器能学习道德吗?德尔菲实验

Can Machines Learn Morality? The Delphi Experiment

Allen Institute for Artificial Intelligence(艾伦人工智能研究所);Paul G. Allen School of Computer Science & Engineering, University of Washington(华盛顿大学保罗·G·艾伦计算机科学与工程学院);York University(约克大学)
Liwei Jiang, Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jenny Liang, Jesse Dodge, Keisuke Sakaguchi, Maxwell Forbes, Jon Borchardt, Saadia Gabriel, Yuli… 展开作者

Liwei Jiang, Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jenny Liang, Jesse Dodge, Keisuke Sakaguchi, Maxwell Forbes, Jon Borchardt, Saadia Gabriel, Yulia Tsvetkov, Oren Etzioni, Maarten Sap, Regina Rini, Yejin Choi

摘要:

随着人工智能系统变得越来越强大和普遍,人们越来越担心机器的道德或缺乏道德。然而,向机器教授道德是一项艰巨的任务,因为道德仍然是人类争论最激烈的问题之一,更不用说人工智能了。然而,部署到数百万用户的现有人工智能系统已经在做出充满道德含义的决策,这提出了一个看似不可能的挑战:教机器道德感,而人类继续与之斗争。为了探索这一挑战,我们引入Delphi,一个基于深度神经网络的实验框架,直接训练来推理描述性的道德判断,例如,“帮助朋友”一般是好的,而“帮助朋友传播假新闻”则不是。实证结果揭示了机器伦理的承诺和局限性的新见解; Delphi在面对新的伦理情况时表现出强大的泛化能力,而现成的神经网络模型表现出明显的判断力差,包括不公正的偏见,证实了明确教导机器道德感的必要性。然而,德尔菲并不完美,表现出普遍的偏见和不一致的敏感性。尽管如此,我们展示了不完美的Delphi的积极用例,包括将其用作其他不完美的AI系统中的组件模型。重要的是,我们解释德尔菲法的操作化突出的伦理理论,这使我们重要的未来研究问题。

英文摘要:

As AI systems become increasingly powerful and pervasive, there are growing concerns about machines' morality or a lack thereof. Yet, teaching morality to machines is a formidable task, as morality remains among the most intensely debated questions in humanity, let alone for AI. Existing AI systems deployed to millions of users, however, are already making decisions loaded with moral implications, which poses a seemingly impossible challenge: teaching machines moral sense, while humanity continues to grapple with it. To explore this challenge, we introduce Delphi, an experimental framework based on deep neural networks trained directly to reason about descriptive ethical judgments, e.g., "helping a friend" is generally good, while "helping a friend spread fake news" is not. Empirical results shed novel insights on the promises and limits of machine ethics; Delphi demonstrates strong generalization capabilities in the face of novel ethical situations, while off-the-shelf neural network models exhibit markedly poor judgment including unjust biases, confirming the need for explicitly teaching machines moral sense. Yet, Delphi is not perfect, exhibiting susceptibility to pervasive biases and inconsistencies. Despite that, we demonstrate positive use cases of imperfect Delphi, including using it as a component model within other imperfect AI systems. Importantly, we interpret the operationalization of Delphi in light of prominent ethical theories, which leads us to important future research questions.

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。

↑