Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble

• URL: http://arxiv.org/abs/2509.11311v1
• Date: Sun, 14 Sep 2025 15:08:45 GMT
• Title: Prompts to Proxies: Emulating Human Preferences via a Compact LLM Ensemble
• Authors: Bingchen Wang, Zi-Yu Khoo, Bryan Kian Hsiang Low,
• Abstract summary: Large language models (LLMs) have demonstrated promise in emulating human-like responses across a range of tasks.<n>We propose a novel alignment framework that treats LLMs as agent proxies for human survey respondents.<n>We introduce P2P, a system that steers LLM agents toward representative behavioral patterns using structured prompt engineering, entropy-based sampling, and regression-based selection.
• Score: 46.82793004650415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) have demonstrated promise in emulating human-like responses across a wide range of tasks. In this paper, we propose a novel alignment framework that treats LLMs as agent proxies for human survey respondents, affording a cost-effective and steerable solution to two pressing challenges in the social sciences: the rising cost of survey deployment and the growing demographic imbalance in survey response data. Drawing inspiration from the theory of revealed preference, we formulate alignment as a two-stage problem: constructing diverse agent personas called endowments that simulate plausible respondent profiles, and selecting a representative subset to approximate a ground-truth population based on observed data. To implement the paradigm, we introduce P2P, a system that steers LLM agents toward representative behavioral patterns using structured prompt engineering, entropy-based sampling, and regression-based selection. Unlike personalization-heavy approaches, our alignment approach is demographic-agnostic and relies only on aggregate survey results, offering better generalizability and parsimony. Beyond improving data efficiency in social science research, our framework offers a testbed for studying the operationalization of pluralistic alignment. We demonstrate the efficacy of our approach on real-world opinion survey datasets, showing that our aligned agent populations can reproduce aggregate response patterns with high fidelity and exhibit substantial response diversity, even without demographic conditioning.

Related papers

• Individual Turing Test: A Case Study of LLM-based Simulation Using Longitudinal Personal Data [54.145424717168794]
  Large Language Models (LLMs) have demonstrated remarkable human-like capabilities, yet their ability to replicate a specific individual remains under-explored.<n>This paper presents a case study to investigate LLM-based individual simulation with a volunteer-contributed archive of private messaging history spanning over ten years.<n>We propose the "Individual Turing Test" to evaluate whether acquaintances of the volunteer can correctly identify which response in a multi-candidate pool most plausibly comes from the volunteer.
  arXiv  Detail & Related papers  (2026-03-01T21:46:27Z)
• Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility [7.616305266104683]
  Large language models (LLMs) are increasingly used as proxies for human judgment in computational social science.<n>We test whether LLM-simulated survey respondents can reproduce human patterns of misinformation belief and sharing.
  arXiv  Detail & Related papers  (2026-02-04T15:48:05Z)
• Population-Aligned Persona Generation for LLM-based Social Simulation [58.8436379542149]
  We propose a systematic framework for synthesizing high-quality, population-aligned persona sets for social simulation.<n>Our approach begins by leveraging large language models to generate narrative personas from long-term social media data.<n>To address the needs of specific simulation contexts, we introduce a task-specific module that adapts the globally aligned persona set to targeted subpopulations.
  arXiv  Detail & Related papers  (2025-09-12T10:43:47Z)
• Large Language Models as Virtual Survey Respondents: Evaluating Sociodemographic Response Generation [18.225151370273093]
  This paper explores a new paradigm: simulating virtual survey respondents using Large Language Models (LLMs)<n>We introduce two novel simulation settings, namely Partial Attribute Simulation (PAS) and Full Attribute Simulation (FAS)<n>We curate a comprehensive benchmark suite, LLM-S3 (Large Language Model-based Sociodemographic Simulation Survey), that spans 11 real-world public datasets across four sociological domains.
  arXiv  Detail & Related papers  (2025-09-08T04:59:00Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework [53.82097200295448]
  Mean-Field LLM (MF-LLM) is first to incorporate mean field theory into social simulation.<n>MF-LLM models bidirectional interactions between individuals and the population through an iterative process.<n> IB-Tune is a novel fine-tuning method inspired by the Information Bottleneck principle.
  arXiv  Detail & Related papers  (2025-04-30T12:41:51Z)
• Synthesizing Public Opinions with LLMs: Role Creation, Impacts, and the Future to eDemorcacy [5.92971970173011]
  This paper investigates the use of Large Language Models to synthesize public opinion data.<n>It addresses challenges in traditional survey methods like declining response rates and non-response bias.<n>We introduce a novel technique: role creation based on knowledge injection.
  arXiv  Detail & Related papers  (2025-03-31T21:21:52Z)
• Human Preferences in Large Language Model Latent Space: A Technical Analysis on the Reliability of Synthetic Data in Voting Outcome Prediction [5.774786149181393]
  We analyze how demographic attributes and prompt variations influence latent opinion mappings in large language models (LLMs)<n>We find that LLM-generated data fails to replicate the variance observed in real-world human responses.<n>In the political space, persona-to-party mappings exhibit limited differentiation, resulting in synthetic data that lacks the nuanced distribution of opinions found in survey data.
  arXiv  Detail & Related papers  (2025-02-22T16:25:33Z)
• Specializing Large Language Models to Simulate Survey Response Distributions for Global Populations [49.908708778200115]
  We are the first to specialize large language models (LLMs) for simulating survey response distributions.<n>As a testbed, we use country-level results from two global cultural surveys.<n>We devise a fine-tuning method based on first-token probabilities to minimize divergence between predicted and actual response distributions.
  arXiv  Detail & Related papers  (2025-02-10T21:59:27Z)
• LLM-Mirror: A Generated-Persona Approach for Survey Pre-Testing [0.0]
  We investigate whether providing respondents' prior information can replicate both statistical distributions and individual decision-making patterns.<n>We also introduce the concept of the LLM-Mirror, user personas generated by supplying respondent-specific information to the LLM.<n>Our findings show that: (1) PLS-SEM analysis shows LLM-generated responses align with human responses, (2) LLMs are capable of reproducing individual human responses, and (3) LLM-Mirror responses closely follow human responses at the individual level.
  arXiv  Detail & Related papers  (2024-12-04T09:39:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.