Aligning Generalisation Between Humans and Machines
🤖 AI Summary
This study addresses the fundamental disparities between human and AI generalization mechanisms—particularly in abstract representation, concept learning, and symbolic reasoning—and their implications for human-AI alignment. We conduct the first systematic cross-disciplinary comparison of generalization across cognitive science and AI, analyzing divergences and convergences along three dimensions: definitional frameworks, modeling approaches, and evaluation paradigms. Building on out-of-distribution generalization theory, neurosymbolic modeling, symbolic reasoning, and cognitive experimental methods, we propose a novel interdisciplinary framework—“cognition-supported AI alignment”—and develop a multi-dimensional generalization mapping with interpretable, cognitively grounded evaluation metrics. Our analysis identifies critical mechanistic gaps and six core interdisciplinary challenges. The work establishes a theoretical foundation and methodological toolkit for advancing trustworthy, interpretable, and cognitively compatible AI alignment. (149 words)
Application Category
📝 Abstract
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.
Problem
Research questions and friction points this paper is trying to address.
Bridging human-AI generalization differences for alignment
Comparing generalization methods across AI and cognitive science
Addressing interdisciplinary challenges in human-AI teaming alignment
Innovation
Methods, ideas, or system contributions that make the work stand out.
Combines AI and cognitive science insights
Maps human and AI generalization differences
Addresses interdisciplinary alignment challenges
🔎 Similar Papers
No similar papers found.
