SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2502.07068 · NAACL · 2025

Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations

Paul Röttger, Daniel Hershcovich, Isabelle Augenstein, Yong Cao, Arnav Arora, Haijiang Liu

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large-scale surveys are essential tools for informing social science research and policy, but running surveys is costly and time-intensive. If one could accurately simulate group-level survey results, this could be very valuable to social science research. Prior work has explored the use of large language models (LLMs) for simulating human behaviors, mostly through prompting. In this paper, we are the first to specialize LLMs for the task of simulating survey response distributions. As a testbed for this task, we use country-level results from two global cultural surveys. We devise a fine-tuning method based on first-token probabilities to minimize divergence between predicted and actual response distributions for a given question. Then, we show that this method substantially outperforms other methods and zero-shot classifiers, even on unseen questions, countries, and a completely unseen survey. While even our best models struggle with the task, especially on unseen questions, our results demonstrate the benefits of specialization for simulation, which may accelerate progress towards sufficiently accurate simulation in the future.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2502.07068")
get_code_for_paper("2502.07068")
have("2502.07068")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2502.07068.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2502.07068.svg)](https://syntology.ai/paper/2502.07068)

Connect an agent — have() is free.