Higher-order representation in AI
Philosophy and the Mind Sciences February 27, 2026 DOI: 10.33735/phimisci.2026.12032 (opens in new tab)
Study at a glance
AI-extracted from the abstract| Characteristics | Review Peer reviewed |
|---|---|
| Keywords | Representation politics Mental representation Metacognition Range aeronautics Empirical evidence Cognitive science Artificial intelligence Epistemology Cognitive psychology Empirical research Natural language processing |
| Key findings | The authors argue that there is some evidence of higher-order representation in large language models, but substantial empirical and philosophical questions remain unresolved. They contend that while LLMs may represent their own inner representational states in activations, the evidence is not definitive and requires further investigation. |
Abstract
Higher-order representations are those that are about other representations. Humans and some other animals form higher-order mental representations concerning representations in our own minds, through the operation of processes of metacognition and introspection. These have been linked with a wide range of mental capacities and attributes, including consciousness. Recent research on large language models (LLMs) has explored their knowledge of their own ‘minds’, sometimes suggesting that these models represent their own inner representational states in activations. This paper surveys this research, arguing that there is some evidence of higher-order representation in LLMs but that substantial empirical and philosophical questions remain unresolved.