Public opinion surveys with large language models: methodological opportunities and validity risks

Abstract Large language models (LLMs) are increasingly being considered as tools for computational social science, yet their implications for survey and public-opinion research remain insufficiently understood. This study examines whether and how they can serve as methodological instruments for estimating aggregate public opinion under out-of-sample conditions. Across three studies, commercial and open-source LLMs are evaluated against recent Pew Research Centre surveys. Study 1 shows that GPT-3.5 and GPT-4 can approximate national-level response distributions more accurately than uniform, normal-distribution, and historical-average baselines, with GPT-4 achieving mean absolute errors of approximately 4–8.5%. However, the models also exhibit important threats to validity, including underrepresentation of Republican viewpoints, underestimation of uncertainty, and, in some cases, overly homogeneous response distributions. Study 2 extends the analysis to GPT-4o, GPT-4o-mini, and Llama 3.3, showing that aggregate predictive accuracy generalises across models but that partisan alignment and distributional fidelity are model- and topic-dependent. Study 3 demonstrates that collective-level estimation is more valid than aggregating persona-based individual simulations, which produce substantially higher error and stronger homogeneity bias. Ablation tests further indicate that predictions are relatively robust to role prompts and temperature settings but sensitive to survey-item context. These findings suggest that LLMs may be useful as exploratory and supplementary tools in public-opinion research. However, the responsible use of LLMs requires explicit validation against human data, attention to bias and uncertainty, and careful integration with established principles of survey design.

Authors

Institutions

Publication Details

Journal
Humanities and Social Sciences Communications
Published
2026-11-17
DOI
https://doi.org/10.1057/s41599-026-09593-8
Primary Topic
Computational and Text Analysis Methods
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Public opinion surveys with large language models: methodological opportunities and validity risks

Pan Liu, Lin Qiu, Tian Xie, Meng-Jie Wang et al.
3 links
Humanities and Social Sciences Communications
Computational and Text Analysis Methods
article

Public opinion surveys with large language models: methodological opportunities and validity risks

Pan Liu, Lin Qiu, Tian Xie, Meng-Jie Wang, Yutong Li
article en

Abstract

Abstract Large language models (LLMs) are increasingly being considered as tools for computational social science, yet their implications for survey and public-opinion research remain insufficiently understood. This study examines whether and how they can serve as methodological instruments for estimating aggregate public opinion under out-of-sample conditions. Across three studies, commercial and open-source LLMs are evaluated against recent Pew Research Centre surveys. Study 1 shows that GPT-3.5 and GPT-4 can approximate national-level response distributions more accurately than uniform, normal-distribution, and historical-average baselines, with GPT-4 achieving mean absolute errors of approximately 4–8.5%. However, the models also exhibit important threats to validity, including underrepresentation of Republican viewpoints, underestimation of uncertainty, and, in some cases, overly homogeneous response distributions. Study 2 extends the analysis to GPT-4o, GPT-4o-mini, and Llama 3.3, showing that aggregate predictive accuracy generalises across models but that partisan alignment and distributional fidelity are model- and topic-dependent. Study 3 demonstrates that collective-level estimation is more valid than aggregating persona-based individual simulations, which produce substantially higher error and stronger homogeneity bias. Ablation tests further indicate that predictions are relatively robust to role prompts and temperature settings but sensitive to survey-item context. These findings suggest that LLMs may be useful as exploratory and supplementary tools in public-opinion research. However, the responsible use of LLMs requires explicit validation against human data, attention to bias and uncertainty, and careful integration with established principles of survey design.

Humanities and Social Sciences Communications
University of Auckland (NZ), Hunan University (CN), Nanyang Technological University (SG), Chinese University of Hong Kong (HK), Wuhan University (CN)
Chinese University of Hong Kong
Computational and Text Analysis Methods
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon