The Emergence of Social Science of Large Language Models
cs.AI
Submitted: 2025-09-29
Updated: 2026-09-05
Comments: The authors have fundamentally reconsidered the scope and study design of this work. The original manuscript no longer accurately represents the research, as the project has since been substantially reconceptualized with a different corpus, methodology, analytical framework, and resulting conclusions. We therefore withdraw this manuscript
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: The social science of large language models (LLMs) examines how these systems evoke mind attributions, interact with one another, and transform human activity and institutions.
Terminology
Abstract
The social science of large language models (LLMs) examines how these systems evoke mind attributions, interact with one another, and transform human activity and institutions. We conducted a systematic review of 270 studies, combining text embeddings, unsupervised clustering and topic modeling to build a computational taxonomy. Three domains emerge organically across the reviewed literature. LLM as Social Minds examines whether and when models display behaviors that elicit attributions of cognition, morality and bias, while addressing challenges such as test leakage and surface cues. LLM Societies examines multi-agent settings where interaction protocols, architectures and mechanism design shape coordination, norms, institutions and collective epistemic processes. LLM-Human Interactions examines how LLMs reshape tasks, learning, trust, work and governance, and how risks arise at the human-AI interface. This taxonomy provides a reproducible map of a fragmented field, clarifies evidentiary standards across levels of analysis, and highlights opportunities for cumulative progress in the social science of artificial intelligence.
Sources
- On the Opportunities and Risks of Foundation Models
- Logistic Regression makes small LLMs strong and explainable "tens-of-shot" classifiers
- The Wisdom of Partisan Crowds: Comparing Collective Intelligence in Humans and LLM-based Agents
- AI Will Always Love You: Studying Implicit Biases in Romantic AI Companions
- Evolution of Social Norms in LLM Agents using Natural Language
- LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
- Evaluating Large Language Models in Theory of Mind Tasks
- Laplacian Dynamics and Multiscale Modular Structure in Networks
- Linear Classifier: An Often-Forgotten Baseline for Text Classification
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals
- Cultural evolution in populations of Large Language Models
- Emergence of human-like polarization among large language model agents
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Emergence of Social Norms in Generative Agent Societies: Principles and Architecture
- Persuasion with Large Language Models: A Survey of Empirical Evidence, Study Methodologies, and Ethical Implications
- Clever Hans or Neural Theory of Mind? Stress Testing Social Reasoning in Large Language Models
- Who is better at math, Jenny or Jingzhen? Uncovering Stereotypes in Large Language Models
- Moral Mimicry: Large Language Models Produce Moral Rationalizations Tailored to Political Identity
- Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection