Machine understanding

2026/05/01 by H.F. Chen, Stephen Grimm, Olga Russakovsky +1 · 1 voice
Computer Science · #Neural Networks and Applications #Machine Learning and Data Classification

paper · doi:10.1016/j.tics.2026.04.003

Abstract

What do artificial intelligence (AI) systems "understand"? This question arises not only in assessing a system's intelligence but also in evaluation practices to ensure the safe and responsible deployment of AI. Drawing on scholarship from philosophy and cognitive science, and informed by current practices in AI, we develop a framework for asking more precise questions and making more precise claims about machine understanding. We conceptualize understanding as a relation between a system (S) and a target of understanding (T), and we discuss how to specify the relation, the system, and the target, offering a landscape of options in each case. Our goal is not to defend a particular account of understanding, but to provide conceptual tools for those working to assess or advance machine understanding.

Citations

• Potemkin Understanding in Large Language Models
• AI models collapse when trained on recursively generated data
• Evaluating the World Model Implicit in a Generative Model
• AI Supported Degradation of the Self Concept: A Theoretical Framework Grounded in Established Cognitive and Computational Mechanisms
• Does ChatGPT have semantic understanding? A problem with the statistics-of-occurrence strategy
• Role play with large language models
• Generative Agents: Interactive Simulacra of Human Behavior
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Training language models to follow instructions with human feedback
• On the Dangers of Stochastic Parrots
• Grounded Language Learning Fast and Slow
• Distilling the Knowledge in a Neural Network
• Science and Core Knowledge
• I.—COMPUTING MACHINERY AND INTELLIGENCE

Cited by

• Mathematical methods and human thought in the age of AI

Discussions

• In a new paper with Huili Chen, Stephen Grimm, and Olga Russakovsky we offer a TAXONOMY of accounts of machine understanding, introducing model-based or ability-based accounts that can be augmented w [bsky, 20 points, 1 comments]

Related

• Do Artificial Intelligence Systems Understand?
• An Essay concerning machine understanding
• A theory of understanding for artificial intelligence: composability, catalysts, and learning
• Understanding in Artificial Intelligence
• Understanding understanding: a renormalization group inspired model of (artificial) intelligence