LLMs and Social Science -- Reading List

An evolving reading list capturing work on the use of LLMs in social science. Feel free to contribute via PR or by messaging me at fossj117 AT gmail DOT com.

Perspectives / Methods

• Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?
• Automated Social Science: Language Models as Scientist and Subjects
• Using large language models in psychology

Reviews

• Large Language Models as Subpopulation Representative Models: A Review

Applications

Human Behavior

• Simulating Human Strategic Behavior: Comparing Single and Multi-agent LLMs

Survey Analysis

• Do AIs know what the most important issue is? Using language models to code open-text social survey responses at scale
• Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information
• Framework-Based Qualitative Analysis of Free Responses of Large Language Models: Algorithmic Fidelity
• AI-Augmented Surveys: Leveraging Large Language Models and Surveys for Opinion Prediction

Critical Perspectives

• Machine Bias. Generative Large Language Models Have a Worldview of Their Own
• Artificial intelligence and illusions of understanding in scientific research
• Large language models cannot replace human participants because they cannot portray identity groups