arXiv 2411.156262025-05-27cs.AI

对齐人类与机器之间的泛化

Aligning Generalisation Between Humans and Machines

Vrije Universiteit Amsterdam（瓦赫宁海姆大学）；University of Bielefeld（比勒菲尔德大学）；NEC Laboratories Europe（NEC欧洲实验室）；University of Bamberg（巴明翰大学）；University of Groningen（格罗宁根大学）；Università di Bologna（博洛尼亚大学）；Meta Reality Labs（Meta现实实验室）；CAIR, Ss. Cyril and Methodius University of Skopje（斯科普里塞尔维亚·克里尔和方法ius大学）；Kansas State University（堪萨斯州立大学）；KU Leuven（根特大学）；University of Edinburgh（爱丁堡大学）；University of Bremen（不莱梅大学）；Paderborn University（帕德博恩大学）；Carnegie Bosch Institute（卡内基·博施研究所）；Università degli Studi di Milano Bicocca（米兰Bicocca大学）；TU Wien（维也纳技术大学）；Fondazione Bruno Kessler（布鲁诺·凯撒基金会）；University College London（伦敦大学学院）；University of British Columbia（不列颠哥伦比亚大学）；Vector Institute（向量研究所）；Duolingo（多邻国）；University of St. Gallen, Institute of Behavioral Science and Technology（圣加尔文大学行为科学与技术研究所）；University of Applied Sciences Mittweida（梅特维达应用科学大学）；Technical University Freiberg（弗赖贝格技术大学）

Filip Ilievski, Barbara Hammer, Frank van Harmelen, Benjamin Paassen, Sascha Saralajew, Ute Schmid, Michael Biehl, Marianna Bolognesi, Xin Luna Dong, Kiril Gash… 展开作者

Filip Ilievski, Barbara Hammer, Frank van Harmelen, Benjamin Paassen, Sascha Saralajew, Ute Schmid, Michael Biehl, Marianna Bolognesi, Xin Luna Dong, Kiril Gashteovski, Pascal Hitzler, Giuseppe Marra, Pasquale Minervini, Martin Mundt, Axel-Cyrille Ngonga Ngomo, Alessandro Oltramari, Gabriella Pasi, Zeynep G. Saribatur, Luciano Serafini, John Shawe-Taylor, Vered Shwartz, Gabriella Skitalinskaya, Clemens Stachl, Gido M. van de Ven, Thomas Villmann

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文结合AI与认知科学的见解，从泛化的概念、方法和评估三个维度分析人类与机器泛化的异同，指出了人机协作对齐中需解决的跨学科挑战。

摘要：

人工智能的最新进展——包括生成式方法——催生了能够支持人类进行科学发现和形成决策的技术，但也可能破坏民主并针对个体。负责任地使用AI及其在人机团队中的参与，日益显示出AI对齐的必要性，即让AI系统按照我们的偏好行事。这些交互中一个关键却常被忽视的方面是人类和机器泛化方式的不同。在认知科学中，人类泛化通常涉及抽象和概念学习。相比之下，AI泛化涵盖机器学习中的域外泛化、符号AI中基于规则的推理，以及神经符号AI中的抽象。在这篇展望论文中，我们结合AI与认知科学的见解，在三个维度上识别泛化的关键共性与差异：泛化的概念、方法和评估。我们沿着这三个维度描绘了AI和认知科学中泛化的不同概念化，并考虑了它们在人机协作对齐中的作用。这催生了AI与认知科学领域的跨学科挑战，必须解决这些挑战才能为人机协作场景中有效且受认知支持的对齐提供基础。

英文摘要：

Recent advances in AI -- including generative approaches -- have resulted in technology that can support humans in scientific discovery and forming decisions, but may also disrupt democracies and target individuals. The responsible use of AI and its participation in human-AI teams increasingly shows the need for AI alignment, that is, to make AI systems act according to our preferences. A crucial yet often overlooked aspect of these interactions is the different ways in which humans and machines generalise. In cognitive science, human generalisation commonly involves abstraction and concept learning. In contrast, AI generalisation encompasses out-of-domain generalisation in machine learning, rule-based reasoning in symbolic AI, and abstraction in neurosymbolic AI. In this perspective paper, we combine insights from AI and cognitive science to identify key commonalities and differences across three dimensions: notions of, methods for, and evaluation of generalisation. We map the different conceptualisations of generalisation in AI and cognitive science along these three dimensions and consider their role for alignment in human-AI teaming. This results in interdisciplinary challenges across AI and cognitive science that must be tackled to provide a foundation for effective and cognitively supported alignment in human-AI teaming scenarios.

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。