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

arXiv: https://arxiv.org/abs/2603.00059 · HTML: https://mlsanity.com/paper/2603.00059/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in LLM synthetic data generation, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 17 of its 72 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Placed in

- Synthetic data and self-improvement for LLMs / [LLM synthetic data generation](https://mlsanity.com/synth/llm-synthetic-data-generation/)

## Builds on (most cited first, 17 of 17)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studies](https://mlsanity.com/paper/2208.10264/) (2022)
- [Prediction-Powered Inference](https://mlsanity.com/paper/2301.09633/) (2023)
- [Thinking Fast and Slow in Large Language Models](https://mlsanity.com/paper/2212.05206/) (2022)
- [Meaning without reference in large language models](https://mlsanity.com/paper/2208.02957/) (2022)
- [Synthetic Data Generation Using Large Language Models: Advances in Text and Code](https://mlsanity.com/paper/2503.14023/) (2025)
- [Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models](https://mlsanity.com/paper/2306.04746/) (2023)
- [Synthetic Data in Human Analysis: A Survey](https://mlsanity.com/paper/2208.09191/) (2022)
- [Vox Populi, Vox AI? Using Language Models to Estimate German Public Opinion](https://mlsanity.com/paper/2407.08563/) (2024)
- [Can AI Serve as a Substitute for Human Subjects in Software Engineering Research?](https://mlsanity.com/paper/2311.11081/) (2023)
- [AIn't Nothing But a Survey? Using Large Language Models for Coding German Open-Ended Survey Responses on Survey Motivation](https://mlsanity.com/paper/2506.14634/) (2025)
- [Bridging Information Gaps with Comprehensive Answers: Improving the Diversity and Informativeness of Follow-Up Questions](https://mlsanity.com/paper/2502.17715/) (2025)
- [Evaluating the Use of Large Language Models as Synthetic Social Agents in Social Science Research](https://mlsanity.com/paper/2509.26080/) (2025)
- [A New Digital Divide? Coder Worldviews, the Slop Economy, and Democracy in the Age of AI](https://mlsanity.com/paper/2510.04755/) (2025)
- [Fully Synthetic Data for Complex Surveys](https://mlsanity.com/paper/2309.09115/) (2023)

## Built on by (most cited first, 2 of 2)

- [The conditional superiority of fast silicon sampling](https://mlsanity.com/paper/2608.14079/) (2026)
- [Shared Autoregressive Context Can Distort Relationships in Synthetic Data](https://mlsanity.com/paper/2609.32546/) (2026)

## Abstract (arXiv)

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.