---
title: "Can language models stand in for survey respondents?"
description: "Survey experiments are a staple of economics, and some researchers now simulate respondents with language models (\"silicon samples\"). Only 6 of 179 recent survey papers carry a language-model keyword, 5 of them in AI journals. Where do simulated answers match real people, and where would they mislead economic research?"
url: https://scholar4ai.com/ideas/language-models-as-survey-respondents
markdown_url: https://scholar4ai.com/ideas/language-models-as-survey-respondents.md
license: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/)
share_text: "Can language models stand in for survey respondents?: Survey experiments are a staple of economics, and some researchers now simulate respondents with language models (\"silicon samples\")."
date: "2026-10-23"
updated: "2026-10-23"
status: "seed"
tags: ["economics", "ai", "methods"]
keywords: ["survey experiment", "large language models"]
---

# Can language models stand in for survey respondents?

Survey experiments are a staple of economics, and some researchers now simulate respondents with language models ("silicon samples"). Only 6 of 179 recent survey papers carry a language-model keyword, 5 of them in AI journals. Where do simulated answers match real people, and where would they mislead economic research?

## What prompted this

Since October 2025, 179 papers carry a survey, questionnaire or respondent keyword (117 in economics journals, 37 in finance). Only 6 of them carry a language-model, ChatGPT or generative-AI keyword, and 5 of those are in AI journals. "Survey experiment" appears on 15 papers, 14 of them in economics.

## Questions

- For published survey experiments in economics, do simulated respondents reproduce the direction and size of the treatment effects?
- Do they capture differences between groups (income, age, country), or flatten them?
- Could they help design and size real surveys, even if they cannot replace them?

## Possible approach

Replicate published survey experiments with language-model respondents given the demographics of the original sample, and compare the effects with the published ones.

## Next step

Pick ten published survey experiments in economics, simulate them with two language models, and compare the estimated treatment effects.

## Related research activity

*The keywords this note follows, in the tracked finance, accounting, economics, management, operations research and AI journals as of 2026-10-26*

| Keyword | Papers, last 30 days | Rank | Papers per month, Oct 23 – Oct 26* | Papers, last 36 months |
|---|---:|---:|---|---:|
| survey experiment | 1 | #2881 | 0, 1, 0, 1, 1, 1, 3, 0, 0, 1, 1, 0, 0, 3, 2, 1, 2, 0, 0, 2, 0, 0, 2, 2, 1, 1, 0, 1, 0, 3, 1, 0, 2, 2, 1, 2, 1 | 37 |
| [large language models](https://scholar4ai.com/keywords/large-language-models.md) | 95 | #1 | 13, 5, 2, 15, 9, 12, 16, 29, 21, 22, 34, 21, 28, 33, 44, 61, 60, 59, 63, 80, 72, 93, 91, 79, 83, 106, 114, 174, 106, 149, 151, 140, 166, 137, 133, 124, 77 | 2,545 |

## Cite this page

Scholar4AI. (2026). Can language models stand in for survey respondents?. Journal Research Rankings. Retrieved October 23, 2026, from https://scholar4ai.com/ideas/language-models-as-survey-respondents

```bibtex
@misc{scholar4ai-ideas-language-models-as-survey-respondents,
  author = {{Scholar4AI}},
  title = {Can language models stand in for survey respondents?},
  year = {2026},
  howpublished = {\url{https://scholar4ai.com/ideas/language-models-as-survey-respondents}},
  urldate = {2026-10-23},
  note = {Journal Research Rankings; data from OpenAlex (CC0); licensed CC BY-NC 4.0}
}
```

License: CC BY-NC 4.0 (https://creativecommons.org/licenses/by-nc/4.0/).