CoChat
Sign Up
Cited by 149Survey Methodology and NonresponseAI in Service InteractionsComputational and Text Analysis Methods

Using large language models to generate silicon samples in consumer and marketing research: Challenges, opportunities, and guidelines

Open access
Sarstedt, Marko, Adler, Susanne J., Rau, Lea, Schmitt, Bernd·2024·Psychology & Marketing
DOI 10.1002/mar.21982
Open this paper in CoChat — free accountOpen PDF

Abstract

Should consumer researchers employ silicon samples and artificially generated data based on large language models, such as GPT, to mimic human respondents' behavior? In this paper, we review recent research that has compared result patterns from silicon and human samples, finding that results vary considerably across different domains. Based on these results, we present specific recommendations for silicon sample use in consumer and marketing research. We argue that silicon samples hold particular promise in upstream parts of the research process such as qualitative pretesting and pilot studies, where researchers collect external information to safeguard follow‐up design choices. We also provide a critical assessment and recommendations for using silicon samples in main studies. Finally, we discuss ethical issues of silicon sample use and present future research avenues.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1002/mar.21982

Cites

59 of 61 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • While LLMs sometimes mimic parameters of human information processing and behavior, this is not always the case.

    “However, while LLMs sometimes mimic parameters of human information processing and behavior, this is not always the case (e.g., Kuric et al. 2026;Sarstedt et al. 2024).”

    From Machine marketing: rethinking the customer in the age of generative AI (2026) · cites this paper as Sarstedt et al. 2024

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

1 retracted

Flagged first, then by citations

Research works printed but not linked: 9

  1. Aher, G., Arriaga, R. I., & Kalai, A. T. (2023). Using large language models to simulate multiple humans and replicate human subject studies. arXiv. http://arxiv.org/pdf/2208.
  2. Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert -Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D. M., Wu, J., Winter, C., & Amodei, D. (2020). Language models are few-shot learners. arXiv. http://arxiv.org/abs/2005.14165 · arXiv
  3. Chang, C.-C., Reitter, D., Aksitov, R., & Sung, Y.-H. (2023). KL-divergence guided temperature sampling. arXiv. http://arxiv.org/abs/2306. 01286
  4. Gao, L., Biderman, S., Black, S., Golding, L., Hoppe, T., Foster, C., Phang, J., He, H., Thite, A., Nabeshima, N., Presser, S., & Leahy, C. (2020). The Pile: An 800GB dataset of diverse text for language modeling. arXiv. https://arXiv.org/pdf/2101.00027.pdf · arXiv
  5. Gemini Team Google, Anil, R., Borgeaud, S., Wu, Y., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A. M., Hauth, A., Millican, K., Silver, D., Petrov, S., Johnson, M., Antonoglou, I., Schrittwieser, J., Glaese, A., Chen, J., Pitler, E., & Vinyals, O. (2023). Gemini: A family of highly capable multimodal models. arXiv. http://arxiv.org/abs/2312.11805 · arXiv
  6. Jiang, H., Zhang, X., Cao, X., & Kabbara, J. (2023). PersonaLLM: Investigating the ability of large language models to express Big Five personality traits. arXiv. http://arxiv.org/abs/2305.02547 · arXiv
  7. Lietz, P. (2010). Research into questionnaire design. International Journal of Market Research, 52(2), 249-272.
  8. McCoy, R. T., Yao, S., Friedman, D., Hardy, M., & Griffiths, T. L. (2023). Embers of autoregression: Understanding large language models through the problem they are trained to solve. arXiv. https://arXiv. org/pdf/2309.13638.pdf
  9. Santurkar, S., Durmus, E., Ladhak, F., Lee, C., Liang, P., & Hashimoto, T. (2023). Whose opinions do language models reflect? arXiv. https:// arxiv.org/pdf/2303.17548 · arXiv

Cited by

Sorted by citations

Related

Authors
Sarstedt, M., Adler, S. J., Rau, L., & Schmitt, B.
Affiliations
  • Babeș-Bolyai University (RO)
  • Ludwig-Maximilians-Universität München (DE)
  • Columbia University (US)
Corresponding author
Sarstedt, Marko
ORCID
Venue
Psychology & Marketing
Publisher
Wiley
Published
2024-02-10
Volume
41
Issue
6
Pages
1254-1270
ISSN
  • 0742-6046 (ISSN-L)
  • 1520-6793
DOI
10.1002/mar.21982
OpenAlex
W4391713857
Cited by
149
References
59
Citations by year
2026: 80 · 2025: 56 · 2024: 13
FWCI
106.52
Type
journal article
Language
en
Open access
Licence
Locations
  • Psychology and Marketing (publishedVersion, cc-by)
  • Open access LMU (Ludwid Maxmilian's Universitat Munchen) (submittedVersion, cc-by)
Topics
  • Social Sciences › Sociology and Political Science › Survey Methodology and Nonresponse
  • Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
Keywords
large language models, GPT, consumer research, market analysis, pilot study, research ethics

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review