Your Next Respondent Might Be an LLM: Guidelines for Using Silicon Samples in Marketing Research
Open accessThe 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.
Integrity signals
Registry
Cites
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.
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?
Understanding similarities and differences in human and agentic information processing is critical for explaining how AI customers make decisions and whether these decisions parallel human decision-making.
“Understanding these similarities as well as differences in human and agentic information processing is critical for explaining how AI customers make decisions and whether these decisions parallel human decision-making (Sarstedt et al. 2026).”
From Machine marketing: rethinking the customer in the age of generative AI (2026) · cites this paper as Sarstedt et al. 2026
The Guidelines for generating valid silicon samples in marketing research (page not provided) say that differences between LLMs and humans may limit how well synthetic respondents capture human decision-making, making validation against human data important. This supports examining whether AI-generated responses parallel human responses, but the paper addresses LLMs as research respondents, not how autonomous AI customers make decisions. (LLM, conf=0.83)
Experimental — accuracy not yet measured
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
Sarstedt, M., Adler, S. J., Rau, L., & Schmitt, B. (2024) · Psychology & Marketing · doi:10.1002/mar.21982 · Cited by 149 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 3
- Brucks, M., & Toubia, O. (2025). Prompt architecture induces methodological artifacts in large language models. PLoS One, 20(4), https://doi.org/10.1371/journal.pone.0319159 · DOI
- Gao, Y., Lee, D., Burtch, G., & Fazelpour, S. (2025). Take caution in using LLMs as human surrogates. Proceedings of the National Academy of Sciences, 122(24), https://doi.org/10.1073/pnas.2501660122 · DOI · Paper page
- Toubia, O., Gui, G. Z., Peng, T., Merlau, D. J., Li, A., & Chen, H. (2025). Twin-2K-500: A data set for building digital twins of over 2,000 people based on their answers to over 500 questions. Marketing Science, 44(6), 1446-1455. https://doi.org/10.1287/mksc.2025.0262 · DOI
Cited by
Sorted by citations
Machine marketing: rethinking the customer in the age of generative AI
Sarstedt, M., Adler, S. J., & Imschloss, M. (2026) · Journal of Marketing Analytics · doi:10.1057/s41270-026-00521-y · Cited by 3 · see citing works
Self-citation
- Authors
- Sarstedt, M., Adler, S. J., Rau, L., & Schmitt, B.
- Affiliations
- Babeș-Bolyai University (RO)
- Ludwig-Maximilians-Universität München (DE)
- Columbia University (US)
- Venue
- NIM Marketing Intelligence Review
- Publisher
- Walter de Gruyter GmbH
- Published
- 2026-04-08
- Volume
- 18
- Issue
- 1
- Pages
- 24-29
- ISSN
- 2628-166X (ISSN-L)
- OpenAlex
- W7153188382
- Cited by
- 2
- References
- 1
- Citations by year
- 2026: 2
- FWCI
- 23.35
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- NIM Marketing Intelligence Review (publishedVersion, cc-by-nc)
- Topics
- Social Sciences › Sociology and Political Science › Survey Methodology and Nonresponse
- Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
- Social Sciences › Sociology and Political Science › Digital Marketing and Social Media
- Keywords
- large language models, participant recruitment, market analysis, survey data collection
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
