Back to search

Article

Humanlike representation of social networks in large language models

2026-08-31

Abstract excerpt

<p>Although large language models (LLMs) have made great progress in their general reasoning capabilities, reasoning about social relationships has remained a challenge. In contrast, humans are naturally skilled at reasoning about how people are connected to one another, even in large, complex social networks. Recent research in cognitive science suggests that a key component of human social intelligence is the ab...

Identifiers and source

Literature Corpus work
3d1dbc70-93d6-5686-983b-f006a5585e63
DOI
10.31234/osf.io/73fpj_v1
Open publication

Related research

Semantic proximity does not establish scientific evidence. Graph snapshot: 2026-09-29.

Click a neighbor to travelStep 1 · 12 closest
Interactive article relationship graphSelect a related publication card to move it into the centre and load its closest explainable connections. Solid lines are source-backed structured connections. Dashed lines are semantic discovery signals and are not scientific evidence.
Humanlike representation of social networks in large language modelsDOI 10.31234/osf.io/73fpj_v1
Reasoning from social information enables efficient human intelligenceSemantic proximity
Medial temporal lobe encodes cognitive maps of real-world social networksSemantic proximity
Discovering and transmitting abstract knowledge over generationsSemantic proximity
Evaluating Large Language Models for Belief Inference: Mapping Belief Networks at ScaleSemantic proximity
On the social nature of abstraction: cognitive implications of interaction and diversitySemantic proximity
Social Semantics: The role of conceptual knowledge and cognitive control in a neurobiological model of the social brainSemantic proximity
The role of detours in individual human navigation patterns of complex networksSemantic proximity
Conceptual maps of social knowledge support trait generalizationSemantic proximity
The Institutional StanceSemantic proximity
From Message Passing to Prompting: Rethinking Graph Learning with Large Language ModelsSemantic proximity
Cognitive network science reveals bias in GPT-3, ChatGPT, and GPT-4 mirroring math anxiety in high-school studentsSemantic proximity
Inferring the internal structure of social collectivesSemantic proximity
Select a neighboring publication to make it the new centre.