The conditional superiority of fast silicon sampling
Not on the map. Why?
Abstract (arXiv)
Silicon sampling can produce surprisingly good population estimates at times. Does doing it fast attenuate such fidelity? In this study, we extend and assess ongoing work in silicon sampling by comparing the algorithmic fidelity of "fast" and "slow" modes of silicon sampling among a nationally representative sample of Singaporean survey respondents. We find that silicon sampling with contemporary frontier models remains a method in early development to be used only with great caution. While silicon samples are able to produce moderately faithful estimates of population means, they continue to understate opinion variance and distort the latent contextual space behind human opinions. Conditional on such limitations, we find "fast" modes of silicon sampling to be relatively superior to traditional "slow" modes of silicon sampling. Fast silicon sampling is significantly more efficient in compute resources and run-time while being monotonically superior to slower modes of sampling in algorithmic fidelity.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 14 of its 48 references that are in the map. First posted on arXiv 14 Aug 2026.
Builds on
14 of 48 references.
References · 14
- 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
- 2023Whose Opinions Do Language Models Reflect?cited by 759
- 2022Out of One, Many: Using Language Models to Simulate Human Samplescited by 737
- 2024Survey of Cultural Awareness in Language Models: Text and Beyondcited by 101
- 2024Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Informationcited by 48
- 2023Exploring the psychology of LLMs' Moral and Legal Reasoningcited by 43
- 2025The threat of analytic flexibility in using large language models to simulate human datacited by 13
- 2024ChatGPT vs Social Surveys: Probing Objective and Subjective Silicon Populationcited by 3
- 2025Guided Persona-based AI Surveys: Can we replicate personal mobility preferences at scale using LLMs?cited by 3
- 2026Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignmentcited by 3
- 2026Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Datacited by 2
- 2026Tastes without distinction: silicon samples and the synthetic construction of tastescited by 2
2 more
- 2026The Collapse of Heterogeneity in Silicon Philosopherscited by 1
- 2026Silicon Sampling via Cross-Survey Transfercited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.