arXiv cs.AI· Zhanzhan Zhao, Yi Yang, Xiao Jia, Zeyun Dong, Chenzhang Wang·· 14 小时前AI 评分31
大语言模型新兴社会科学研究全景图：198 篇精选论文与 47,719 篇文献的计算映射
Mapping the Emerging Social Science of Large Language Models
AI 导读
一项研究结合 198 篇精选论文综述与五大数据库 47,719 篇正式发表论文的计算映射，将 LLM 社会科学研究划分为三大领域下的 13 个子类：LLM 作为社会心智、LLM 社会、LLM-人类交互。结构主题建模追踪了研究关注点随时间与发表渠道的变化，并指出当前对 LLM 认知与社会行为背后机制的理解仍存空白，呼吁在三大领域建立共享基准与稳健性检验。
正文 · 原文
Abstract:As large language models (LLMs) blur the boundary between cognition and computation, they reshape knowledge production and collective life. We combine a curated review of 198 papers with computational mapping of 47,719 formally published papers from five databases. Text embeddings, clustering, and topic modeling organize the curated literature into 13 subcategories across three domains. LLM as Social Minds examines mind-like reasoning and socially grounded behavior in individual models. LLM Societies explores how interactions among agents produce collective behavior and social organization. LLM-Human Interactions examines how people perceive and engage with LLMs, and how interaction reshapes human thinking, creativity, and relationships. Structural topic modeling of the larger corpus traces how research attention shifts over time and differs across publication venues. We present a reproducible framework that identifies the field's underlying structure and enables its continuous refinement as new studies emerge. The review also identifies a gap in current understanding: the mechanisms underlying many of LLMs' observed cognitive and social behaviors remain unclear. Human-like performance can then be mistaken for understanding, obscuring the norms, biases, and structures of power that LLMs reproduce. We call for shared benchmarks and robustness checks across the three domains to build a reliable evidence base for understanding LLMs' social behaviors and informing their design and use.
| Subjects: | Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.07598 [cs.CY] |
| (or arXiv:2609.07598v2 [cs.CY] for this version) | |
| https://doi.org/10.48550/arXiv.2609.07598 arXiv-issued DOI via DataCite |
Submission history
From: Zhanzhan Zhao [view email]
[v1]
Mon, 7 Sep 2026 15:08:15 UTC (4,833 KB)
[v2]
Thu, 29 Oct 2026 14:08:25 UTC (4,864 KB)
来源：arXiv cs.AI · arxiv.org