Discussion of AI alignment (alignment between humans and AI systems) has focused on value alignment, broadly referring to creating AI systems that share human values. We argue that before we can even attempt to align values, it is imperative that AI systems and humans align the concepts they use to understand the world. We integrate ideas from philosophy, cognitive science, and deep learning to explain the need for concept alignment, not just value alignment, between humans and machines. We summarize existing accounts of how humans and machines currently learn concepts, and we outline opportunities and challenges in the path towards shared concepts. Finally, we explain how we can leverage the tools already being developed in cognitive science and AI research to accelerate progress towards concept alignment.
Human-like Cognitive Generalization for Large Models via Brain-in-the-loop Supervision
College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);State Key Lab of Brain-Machine Intelligence, Zhejiang University(浙江大学脑机智能全国重点实验室)
Concept-Aware Latent and Explicit Knowledge Integration for Enhanced Cognitive Diagnosis
School of Information Science and Engineering, Shandong Normal University(山东师范大学信息科学与工程学院);School of Journalism and Communication, Shandong Normal University(山东师范大学新闻与传媒学院)
Alien Recombination: Exploring Concept Blends Beyond Human Cognitive Availability in Visual Art
Max Planck Institute for Human Development(马克斯·普朗克人类发展研究所);Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所);NVIDIA(英伟达公司);Tallinn University(塔林大学)
Sleep Brain and Cardiac Activity Predict Cognitive Flexibility and Conceptual Reasoning Using Deep Learning
Laboratoire d’imagerie, de vision et d’intelligence artificielle (LIVIA), École de technologie supérieure (ÉTS), Université du Québec(图像、视觉和人工智能实验室(LIVIA),工程学院(ÉTS),魁北克大学);Ouraring Inc(Ouraring公司);Center for Health Sciences, SRI International(健康科学中心,SRI国际)
A Cognitive Explainer for Fetal ultrasound images classifier Based on Medical Concepts
Tsinghua Shenzhen International Graduate School(清华大学深圳国际研究生院);University Town of Shenzhen, Nanshan District, Shenzhen(深圳大学城南山区深圳校区);Beijing Tsinghua Changgung Hospital(北京清华大学长庚医院);Peking University Shenzhen Hospital(北京大学深圳医院);Shenzhen Baoan District Maternal and Child Health Hospital(深圳宝安区妇幼保健医院)
Detecting Alzheimer's Disease by estimating attention and elicitation path through the alignment of spoken picture descriptions with the picture prompt
University of Sheffield(谢菲尔德大学);Royal Hallamshire Hospital(皇家哈勒姆医院);Sheffield Institute for Translational Neuroscience(谢菲尔德转化神经科学研究所)
Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers
Fraunhofer Heinrich-Hertz-Institute(弗劳恩霍夫海因茨·赫兹研究所);Technische Universität Berlin(柏林工业大学);BIFOLD – Berlin Institute for the Foundations of Learning and Data(柏林学习与数据基础研究所(BIFOLD));Carl von Ossietzky Universität Oldenburg(卡尔·冯·奥西茨基奥尔登堡大学)