This repository curates academic papers exploring the intersection of Large Language Models (LLMs) and social science. It targets researchers and practitioners in fields like psychology, sociology, and political science, providing a structured overview of LLM evaluations, alignment strategies, and applications in social research. The collection aims to foster understanding of LLMs' societal impact and potential.

How It Works

The repository categorizes papers based on their focus within social science research, including surveys, datasets, LLM evaluation (values, personality, morality, opinion, ability, risk), tool enhancement, alignment, simulation, and perspectives. This structured approach allows users to quickly find relevant literature on specific aspects of LLMs in social science.

Quick Start & Requirements

This is a curated list of academic papers, not a software package. No installation or execution is required. Links to papers and, where available, code repositories are provided.

Highlighted Details

• Extensive coverage of LLM evaluation across psychological and social dimensions (values, personality, morality).
• Focus on LLM alignment with human values and societal norms.
• Numerous papers on using LLMs for social simulation and agent-based modeling.
• Includes links to datasets and code for many cited works.

Maintenance & Community

The repository is maintained by ValueByte-AI. It encourages contributions and discussions from the community. Specific contributors or community channels are not detailed in the README.

Licensing & Compatibility

The repository itself is not software and does not have a software license. The licensing of the linked papers and code repositories would need to be checked individually.

Limitations & Caveats

This is a bibliography and not an executable tool. The content is a snapshot of research and may not include the very latest publications. Some linked code repositories may have their own dependencies or maintenance status.