Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data

Jason Miklian, Kristian Hoelscher & John E. Katsos

arXiv preprint arXiv:2603.00059, 2026

DOI: 10.2139/ssrn.6210099

Read the full paper →
How well can AI-derived synthetic research data replicate the responses of human participants? An emerging literature has begun to engage with this question, which carries deep implications for organizational research practice. This article presents a comparison between a human-respondent survey of 420 Silicon Valley coders and developers and synthetic survey data designed to simulate real survey takers generated by five leading Generative AI Large Language Models: ChatGPT Thinking 5 Pro, Claude Sonnet 4.5 Pro plus Claude CoWork 1.123, Gemini Advanced 2.5 Pro, Incredible 1.0, and DeepSeek 3.2. Our findings reveal that while AI agents produced technically plausible results that lean more towards replicability and harmonization than assumed, none were able to capture the counterintuitive insights that made the human survey valuable. Moreover, deviations grouped together for all models, leaving the real data as the outlier. Our key finding is that while leading LLMs are increasingly being used to scale, replicate and replace human survey responses in research, these advances only show an increased capacity to parrot conventional wisdom in harmony with each other rather than revealing novel findings. If synthetic respondents are used in future research, we need more replicable validation protocols and reporting standards for when and where synthetic survey data can be used responsibly, a gap that this paper fills. Our results suggest that synthetic survey responses cannot meaningfully model real human social beliefs within organizations, particularly in contexts lacking previously documented evidence. We conclude that synthetic survey-based research should be cast not as a substitute for rigorous survey methods, but as an increasingly reliable pre- or post-fieldwork instrument for identifying societal assumptions, conventional wisdoms, and other expectations about research populations.

Key Messages

  • Five leading LLMs generated synthetic respondents for a survey instrument previously fielded with 420 Silicon Valley coders and developers; all produced technically plausible results leaning toward replicability and harmonization.
  • No model captured the counterintuitive insights that made the human survey valuable, and model deviations grouped together, leaving the real human data as the outlier.
  • Synthetic survey responses cannot meaningfully model real human social beliefs within organizations, particularly in contexts lacking previously documented evidence.
  • Synthetic respondents are best cast as pre- or post-fieldwork instruments for identifying conventional wisdoms and societal assumptions, not substitutes for rigorous survey methods; the paper proposes validation protocols and reporting standards.

Research Topics

LLMs synthetic data AI research methods survey methodology

Citation

Jason Miklian, Kristian Hoelscher, and John E. Katsos. "Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data." arXiv preprint arXiv:2603.00059, 2026. https://doi.org/10.48550/arXiv.2603.00059

Related Research Areas

BibTeX Citation 
@article{miklian2026_stochastic_parrots_or_singing,
  title = {Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data},
  author = {Miklian, Jason and Hoelscher, Kristian and Katsos, John E.},
  journal = {Preprint},
  year = {2026},
  url = {https://arxiv.org/abs/2603.00059}
}