The conditional superiority of fast silicon sampling

Nickolas Hock Yuen Lam; Ji Xuan Voo; Xiangyu Ma

cs.CLAug 14, 2026

The conditional superiority of fast silicon sampling

Authors: Nickolas Hock Yuen Lam, Ji Xuan Voo, Xiangyu Ma

Organizations: Nanyang Technological University, Singapore

Abstract

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.

Figures & tables

Figure 1. Cumulative use of slow and fast silicon sampling in preprints over time

Figure 2. Process of slow and fast silicon sampling

	Runtime		Tokens		Cost (USD)
	Per run (s)	Aggregate (hr)	Per run	Aggregate (M)	Per run	Aggregate
Slow Sampling	20	335.3	4,000	241.440	$0.010	$603.60
Fast Sampling	3	50.3	1,450	87.522	$0.005	$301.80

Table 1. Costs of slow and fast silicon sampling

	WVS	Slow sampling		Fast sampling
	Mean	Mean	Delta	Mean	Delta
Immigration
Fills impt. job vacancies	1.24	2.00	0.76 [0.87]	2.00	0.75 [0.86]
Strengthens cultural diversity	1.20	1.94	0.74 [0.85]	1.91	0.72 [0.83]
Decreases crime	1.04	1.51	0.47 [0.55]	1.08	0.04 [0.05]
Provides asylum to the persecuted	0.52	1.76	1.24 [1.51]	1.30	0.79 [0.96]

Table 2. Comparison of Means from Slow and Fast Silicon Sampling

	Slow sampling		Fast sampling
	Mean	SD	Mean	SD	$\Delta$ (Slow $-$ Fast)
Immigration attitudes	0.602	0.183	0.590	0.188	$0.012$ ***
Moral attitudes	0.589	0.142	0.569	0.149	$0.020$ ***

Table 3. Jaccard Distance Between Silicon Sample Respondents and Their Matched WVS Respondent

Immigration
	WVS	Slow sampling		Fast sampling
	SD	SD	Delta	SD	Delta
Fills impt. job vacancies	0.87	0.01	-0.86***	0.03	-0.84***
Strengthens cultural diversity	0.87	0.21	-0.66***	0.25	-0.62***
Decreases crime	0.86	0.51	-0.35***	0.41	-0.45***
Provides asylum to the persecuted	0.82	0.31	-0.51***	0.38	-0.44***

Table 4. Comparison of Standard Deviations from Slow and Fast Silicon Sampling

	Correlation with WVS			Mean deviation from WVS		Slow vs. fast
	Slow	Fast	Bootstrap	Slow	Fast	Correlation	Mean $\|\Delta\|$	Max $\|\Delta\|$
Opinions w.r.t. immigration	0.28	0.42	0.998	$-0.167$	$-0.123$	0.62	0.171	0.50
Opinions w.r.t. ethical norms	0.57	0.69	1.000	$+0.060$	$+0.018$	0.93	0.066	0.30

Table 5. Summary Statistics for Pairwise Cramer’s V Association Matrices

Panel of Figure 3 — Figure 3. Deviation in Cramer’s V for immigration attitudes

Panel of Figure 4 — Figure 4. Deviation in Cramer’s V for moral attitudes

Figure 5. MCA Biplots of Attitudes Towards Immigration and Ethical Norms

Figure 6. MCA Biplots of Attitudes Towards Immigration and Ethical Norms (continued)

Panel of Figure 7 — Figure 7. Procrustes Alignment of Silicon and WVS MCA Configurations

			Tucker’s $\varphi$
	Source	$M^{2}$	Dim. 1	Dim. 2
Attitudes towards Immigration	Slow	0.610	0.683	0.580
	Fast	0.468	0.769	0.688
	Bootstrap	0.000	1.000	1.000
Ethical Norms	Slow	0.744	0.487	0.585
	Fast	0.756	0.484	0.597

Table 6. Procrustes statistics comparing MCA configurations against the WVS

Explore similar work

Silicon Sampling via Cross-Survey Transfer
Jul 3, 2026Chan-Tung Ku, Chan Hsu, Pei-Cing Huang +3LLM Evaluation Transfer Learning
Department of Information Management National Sun Yat-sen University Kaohsiung, Taiwan · Institute of Political Science National Sun Yat-sen University Kaohsiung, Taiwan · Graduate Institute of Library and Information Science National Chung Hsing University Taichung, Taiwan
Data Quality Profiling at Scale with Progressive Sampling: A Benchmark for Data-Centric AI Pipelines
Jul 28, 2026Laure Berti-EquilleImportance Sampling Adaptive Sampling
IRD, ESPACE-DEV, 500, rue Jean-François Breton, 34093 Montpellier, France
Tastes without distinction: silicon samples and the synthetic construction of tastes
Jun 29, 2026Xiangyu Ma, Mengmi Zhang, Shannon Ang +1Synthetic Data Generation Cultural Bias in Language Models
Nanyang Technological University, Singapore

Jul 3, 2026, cs.AIJ/K move · Enter open · S save

Silicon Sampling via Cross-Survey Transfer

Chan-Tung Ku, Chan Hsu, Pei-Cing Huang, Frank Cheng-shan Liu+2

Department of Information Management National Sun Yat-sen University Kaohsiung, Taiwan · Institute of Political Science National Sun Yat-sen University Kaohsiung, Taiwan · Graduate Institute of Library and Information Science National Chung Hsing University Taichung, Taiwan

LLM Evaluation Transfer Learning

Open paper AskPDF arXiv

Silicon sampling-using large language models (LLMs) to simulate human survey respondents-has emerged as a promising approach for augmenting traditional survey research. However, most evaluations rely on distributional comparisons rather than individual-level prediction, which risks conflating pattern matching with coherent respondent-level prediction. We propose cross-survey transfer, a more rigorous evaluation framework in which an LLM is given a respondent's answers to one set of questions and must predict their answers to entirely different questions from the same survey. Using data from the Taiwan Election and Democratization Study (TEDS) 2024, three open-weight LLMs (27B-120B parameters), and supervised machine learning baselines, we find that: (1) zero-shot LLMs achieve 52% accuracy on genuinely unseen items, closing to within 6 percentage points (pp) of a supervised random forest trained on same-population data; (2) a stable construct predictability hierarchy emerges, from 67% for partisan attitudes to 23% for sovereignty; and (3) variance collapse and safety alignment effects-two commonly cited LLM limitations-turn out to be more nuanced than previously reported, with variance collapse affecting supervised models as well and alignment effects varying dramatically across model families. These findings clarify both the promise and boundaries of silicon sampling.

Abstract

Explore similar work

Silicon Sampling via Cross-Survey Transfer

Data Quality Profiling at Scale with Progressive Sampling: A Benchmark for Data-Centric AI Pipelines

Tastes without distinction: silicon samples and the synthetic construction of tastes