# The conditional superiority of fast silicon sampling

arXiv: https://arxiv.org/abs/2608.14079 · HTML: https://mlsanity.com/paper/2608.14079/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 14 Aug 2026.

## Builds on (most cited first, 14 of 14)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Survey of Cultural Awareness in Language Models: Text and Beyond](https://mlsanity.com/paper/2411.00860/) (2024)
- [Random Silicon Sampling: Simulating Human Sub-Population Opinion Using a Large Language Model Based on Group-Level Demographic Information](https://mlsanity.com/paper/2402.18144/) (2024)
- [Exploring the psychology of LLMs' Moral and Legal Reasoning](https://mlsanity.com/paper/2308.01264/) (2023)
- [The threat of analytic flexibility in using large language models to simulate human data](https://mlsanity.com/paper/2509.13397/) (2025)
- [Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment](https://mlsanity.com/paper/2604.12851/) (2026)
- [ChatGPT vs Social Surveys: Probing Objective and Subjective Silicon Population](https://mlsanity.com/paper/2409.02601/) (2024)
- [Guided Persona-based AI Surveys: Can we replicate personal mobility preferences at scale using LLMs?](https://mlsanity.com/paper/2501.13955/) (2025)
- [Stochastic Parrots or Singing in Harmony? Testing Five Leading LLMs for their Ability to Replicate a Human Survey with Synthetic Data](https://mlsanity.com/paper/2603.00059/) (2026)
- [The Collapse of Heterogeneity in Silicon Philosophers](https://mlsanity.com/paper/2604.23575/) (2026)
- [Tastes without distinction: silicon samples and the synthetic construction of tastes](https://mlsanity.com/paper/2606.30085/) (2026)
- [Silicon Sampling via Cross-Survey Transfer](https://mlsanity.com/paper/2607.03091/) (2026)

## Built on by (most cited first, 1 of 1)

- [Shared Autoregressive Context Can Distort Relationships in Synthetic Data](https://mlsanity.com/paper/2609.32546/) (2026)

## 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.