Social science research maps three key areas of large language models
Mapping the Emerging Social Science of Large Language Models
Computers and SocietyArtificial IntelligenceComputation and Language
Summary
Large language models (LLMs) are changing how people communicate and work, but research about their social impacts is scattered. The authors looked at nearly 200 key papers and almost 48,000 papers overall to organize this research into three main areas: how LLMs behave like social minds, how multiple LLMs interact like societies, and how humans interact with LLMs. They identified detailed topics like reasoning, creativity, trust, and bias across these areas. This mapping helps others understand how LLMs affect social and institutional contexts.
What this means in practice
- •For social scientists: Use the taxonomy to organize and focus studies on how LLM behavior and interactions impact social outcomes.
- •For conference organizers: Design calls for papers and review tracks aligned with the three domains to better structure LLM social science research.
A survey. It maps existing work.
Authors
Yi Yang, Xiao Jia, Zeyun Dong, Chenzhang Wang, Zhanzhan Zhao
Abstract
Large language models (LLMs) increasingly shape communication, learning, work, creativity, and decision-making, yet social-science research on these developments remains fragmented. We map this emerging field using a curated corpus of 198 papers reviewed in full and a field-scale corpus of 47,719 published papers from five bibliographic databases. Combining sentence embeddings, K-means clustering, within-cluster Latent Dirichlet Allocation (LDA), author and LLM classifications, and structural topic modeling, we identify three domains: LLM as Social Minds, examining socially interpretable model behavior; LLM Societies, examining collective dynamics among interacting model-based agents; and LLM-Human Interactions, examining how people perceive, use, and are affected by LLMs. These domains contain 13 subcategories spanning reasoning, personality and bias, behavioral games, collective intelligence, simulation, trust, work, creativity, and education. In the curated corpus, the three-domain solution is highly stable under resampling (adjusted Rand index = 0.952), and K-means assignments agree with author full-text classifications for 77.78% of papers. At field scale, 13 of 15 topics map onto the taxonomy, while K-means and structural-topic-model domains agree for 73.83% of overlapping papers. LLM-Human Interactions accounts for 78.02% of domain-mapped topic mass, but venue analysis reveals a contrasting pattern: Social Minds and LLM Societies together account for 66.37% of highly cited papers in leading conference venues, whereas LLM-Human Interactions accounts for 76.81% in the corresponding journal subset. The resulting taxonomy provides a reproducible framework for understanding how model behavior, agent interaction, and institutional context jointly shape the social consequences of LLMs.