NeuroCogMap Reveals Cognitive Organization of Large Language Models

2026-06-30

AI Summary

It remains unclear whether large language models possess human-like, interpretable organization of cognitive functions within their internal representations. Inspired by cognitive neuroscience, this work proposes the first system-level framework that partitions model internals into stable, semantically coherent functional modules, thereby constructing a hierarchical cognitive map. By integrating functional decomposition, representational analysis, neural alignment, and cognitive modeling—alongside neuroimaging data collected during natural language tasks—the study reveals systematic correspondences between model functional organization and human cortical responses as well as cognitive strategies. This approach not only identifies internal representational signatures underlying failure modes such as hallucination and bias but also substantially improves prediction of higher-order cortical activity and enhances models of human decision-making.

Abstract

Understanding how complex cognitive functions are organized within artificial systems is central to interpreting large language models (LLMs) and relating them to biological cognition. Yet although LLMs exhibit broad cognitive-like behaviours, it remains unclear whether their internal representations form reproducible functional systems that explain behaviour, failure and links to human cognition. Here we present NeuroCogMap, a cognitive neuroscience-inspired framework that organizes internal features of LLMs into functional parcels and links them to interpretable functions, cognitive capabilities and a cognitive hierarchy. These parcels form a stable and semantically coherent organization that is partly conserved across models and functionally linked to model outputs. Within this organization, major LLM failures, including hallucination, bias, refusal failure and sycophancy, correspond to distinct disruptions in representational and behavioural-control systems, yielding internal signatures for mechanism-guided detection and targeted intervention. Beyond model behaviour, NeuroCogMap improves prediction of human cortical responses during naturalistic language comprehension, with the strongest correspondence in higher-order association cortex. At the cognitive level, its internal signatures expose latent strategies that guide refinements of classical models of human decision-making. Together, these findings establish NeuroCogMap as a system-level framework for mapping functional organization in artificial systems and for relating this organization to human cortical function and cognitive behaviour.

Problem

• large language models
• cognitive organization
• functional systems
• model failures
• human cognition

Innovation

• NeuroCogMap
• functional organization
• large language models
• cognitive neuroscience
• mechanism-guided intervention