Year: 2024
Type: preprint
Abstract: 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.
Source: arXiv (Cornell University)
Institutions: Princeton University, University of California, Merced
Language: English
Subfield: Safety Research
Field: Social Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W4391012748