Article

Synthetic survey participants cannot substitute for sample diversity in policy

2026-07-27

Abstract excerpt

<p>Synthetic survey participants generated by large language models (LLMs) have recently been promoted as a means of reaching diverse and underrepresented populations in policy research. We argue that this promise rests on a mistaken equivalence between demographic labelling and meaningful representation. Because LLM training corpora disproportionately reflect Western, English-language, and third-person accounts,...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: c73705b3-c0f4-58cb-884a-5fa2a2b7e5f1
DOI: 10.31234/osf.io/8x37h_v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Synthetic survey participants cannot substitute for sample diversity in policyDOI 10.31234/osf.io/8x37h_v1Read

Designing, Evaluating, and Using Synthetic Participants in Behavioural Public Policy: The PATH ChecklistSemantic proximity Read

Synthetic Participants Generated by Large Language Models: A Systematic Literature ReviewSemantic proximity Read

Large Language Models as Synthetic Respondents for Economic Preferences: A Global AuditSemantic proximity Read

Synthetic Policymaking: Using LLM-Generated Personas to Predict Public Views on Existing and Prospective Policies in non-WEIRD CountriesSemantic proximity Read

AI as a Research Proxy: Navigating the New Frontier of Social Science Inquiry through Language ModelsSemantic proximity Read

Study planning is better served by Monte Carlo simulation than AI-generated participantsSemantic proximity Read

The threat of synthetic respondents extends to clinical mental health screeningSemantic proximity Read

Digital shadows in mental health map how LLMs simulate depression, anxiety, and stress through language and psychometricsSemantic proximity Read

Digital shadows in mental health map how LLMs simulate depression, anxiety, and stress through language and psychometricsSemantic proximity Read

Large language models as linguistic simulators and cognitive models in human researchSemantic proximity Read

Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behaviorSemantic proximity Read

Digital shadows in mental health map how LLMs simulate depression, anxiety, and stress through language and psychometricsSemantic proximity Read