绘制大语言模型新兴社会科学图景

中文摘要 AI 辅助

大语言模型（LLMs）日益塑造着沟通、学习、工作、创造力和决策，然而关于这些发展的社会科学研究仍然零散。我们利用一个由198篇全文审阅论文组成的精选语料库，以及来自五个文献数据库的47,719篇已发表论文的领域规模语料库，来绘制这一新兴领域。结合句子嵌入、K均值聚类、聚类内潜在狄利克雷分配（LDA）、作者与LLM分类以及结构主题建模，我们识别出三个领域：LLM作为社会心智，考察社会可解释的模型行为；LLM社会，考察基于模型的智能体之间的集体动态；以及LLM-人类交互，考察人们如何感知、使用LLM并受其影响。这些领域包含13个子类别，涵盖推理、人格与偏见、行为博弈、集体智能、模拟、信任、工作、创造力和教育。在精选语料库中，三领域方案在重采样下高度稳定（调整兰德指数=0.952），K均值分配与作者全文分类在77.78%的论文中一致。在领域规模上，15个主题中有13个映射到该分类体系，而K均值与结构主题模型领域在73.83%的重叠论文中一致。LLM-人类交互占领域映射主题质量的78.02%，但场所分析揭示了一个对比模式：社会心智与LLM社会合计占领先会议场所高被引论文的66.37%，而LLM-人类交互在相应期刊子集中占76.81%。由此产生的分类体系为理解模型行为、智能体交互和制度背景如何共同塑造LLM的社会后果提供了一个可复现的框架。

英文摘要

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.

发表机构

• The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
• Xidian University（西安电子科技大学）
• The University of Edinburgh（爱丁堡大学）

机构由 AI 辅助整理，请以论文原文为准。