Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science Research

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Madden, Emma Rose
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918174515003392
author Madden, Emma Rose
author_facet Madden, Emma Rose
contents Large Language Models (LLMs) are being increasingly used as synthetic agents in social science, in applications ranging from augmenting survey responses to powering multi-agent simulations. This paper outlines cautions that should be taken when interpreting LLM outputs and proposes a pragmatic reframing for the social sciences in which LLMs are used as high-capacity pattern matchers for quasi-predictive interpolation under explicit scope conditions and not as substitutes for probabilistic inference. Practical guardrails such as independent draws, preregistered human baselines, reliability-aware validation, and subgroup calibration, are introduced so that researchers may engage in useful prototyping and forecasting while avoiding category errors.
format Preprint
id arxiv_https___arxiv_org_abs_2509_26080
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science Research
Madden, Emma Rose
Artificial Intelligence
Applications
Large Language Models (LLMs) are being increasingly used as synthetic agents in social science, in applications ranging from augmenting survey responses to powering multi-agent simulations. This paper outlines cautions that should be taken when interpreting LLM outputs and proposes a pragmatic reframing for the social sciences in which LLMs are used as high-capacity pattern matchers for quasi-predictive interpolation under explicit scope conditions and not as substitutes for probabilistic inference. Practical guardrails such as independent draws, preregistered human baselines, reliability-aware validation, and subgroup calibration, are introduced so that researchers may engage in useful prototyping and forecasting while avoiding category errors.
title Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science Research
topic Artificial Intelligence
Applications
url https://arxiv.org/abs/2509.26080