Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles

• URL: http://arxiv.org/abs/2608.15871v1
• Date: Sun, 16 Aug 2026 17:39:57 GMT
• Title: Large Language Models as Implicit Sociological Models: Reconstructing Voting Behaviour from Sociodemographic Profiles
• Abstract summary: Large language models (LLMs) trained on large-scale internet corpora encode extensive statistical regularities about social identities, attitudes, and political behaviour.<n>This paper introduces and evaluates a methodological framework that leverages these latent representations to reconstruct aggregate voting behaviour from individual-level sociodemographic profiles.
• Score: 1.7299313638653595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models (LLMs) trained on large-scale internet corpora encode extensive statistical regularities about social identities, attitudes, and political behaviour. This paper introduces and evaluates a methodological framework that leverages these latent representations to reconstruct aggregate voting behaviour from individual-level sociodemographic profiles. We operationalize LLMs as implicit sociological models by conditioning them on demographic descriptions, eliciting probabilistic turnout and party preferences, and aggregating individual outputs via a soft voting procedure. Using the 2021 Czech parliamentary election as a validation case, we demonstrate that contemporary LLMs reproduce official election outcomes with low mean absolute error, recover known political bloc structures, and align with independently established sociodemographic gradients. The contribution of this work is methodological rather than predictive: we show how LLMs can be systematically interrogated as compressed representations of social reality, offering a novel exploratory instrument for computational social science while clearly delineating its epistemic and ethical limits.

Related papers

• Shaping Schema via Language Representation as the Next Frontier for LLM Intelligence Expanding [88.11781604392606]
  This paper defines language representation as the linguistic and symbolic constructs used to map and model the real world.<n>We argue that shaping schemas through advanced language representation is the next frontier for expanding Large Language Models.
  arXiv  Detail & Related papers  (2026-05-10T02:42:29Z)
• Parametric Social Identity Injection and Diversification in Public Opinion Simulation [26.236052138777186]
  Large language models (LLMs) have recently been adopted as synthetic agents for public opinion simulation.<n>Despite their scalability, current simulation methods fail to capture social diversity.<n>We propose Parametric Social Identity Injection (PSII), a general framework that injects explicit, parametric representations of demographic attributes.
  arXiv  Detail & Related papers  (2026-03-17T05:52:03Z)
• Interpretable Debiasing of Vision-Language Models for Social Fairness [55.85977929985967]
  We introduce an interpretable, model-agnostic bias mitigation framework, DeBiasLens, that localizes social attribute neurons in Vision-Language models.<n>We train SAEs on facial image or caption datasets without corresponding social attribute labels to uncover neurons highly responsive to specific demographics.<n>Our research lays the groundwork for future auditing tools, prioritizing social fairness in emerging real-world AI systems.
  arXiv  Detail & Related papers  (2026-02-27T13:37:11Z)
• Population-Aligned Persona Generation for LLM-based Social Simulation [58.84363795421489]
  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)
• The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for Large Language Models [7.819021910077221]
  We examine how different persona prompt strategies influence large language models (LLMs)<n>We find that the choice of demographic priming and role adoption strategy significantly impacts their portrayal.<n>Specifically, we find that prompting in an interview-style format and name-based priming can help reduce stereotyping.
  arXiv  Detail & Related papers  (2025-07-21T21:23:29Z)
• Beyond Demographics: Fine-tuning Large Language Models to Predict Individuals' Subjective Text Perceptions [33.76973308687867]
  We show that models do improve in sociodemographic prompting when trained.<n>This performance gain is largely due to models learning annotator-specific behaviour rather than sociodemographic patterns.<n>Across all tasks, our results suggest that models learn little meaningful connection between sociodemographics and annotation.
  arXiv  Detail & Related papers  (2025-02-28T09:53:42Z)
• A Large-Scale Simulation on Large Language Models for Decision-Making in Political Science [18.521101885334673]
  We develop a theory-driven, multi-step reasoning framework to simulate voter decision-making at scale.<n>We conduct large-scale simulations of recent U.S. presidential elections using synthetic personas calibrated to real-world voter data.
  arXiv  Detail & Related papers  (2024-12-19T07:10:51Z)
• Designing Domain-Specific Large Language Models: The Critical Role of Fine-Tuning in Public Opinion Simulation [0.0]
  This paper introduces a novel fine-tuning approach that integrates socio-demographic data from the UK Household Longitudinal Study.<n>By emulating diverse synthetic profiles, the fine-tuned models significantly outperform pre-trained counterparts.<n>Its broader implications include deploying LLMs in domains like healthcare and education, fostering inclusive and data-driven decision-making.
  arXiv  Detail & Related papers  (2024-09-28T10:39:23Z)
• Social Debiasing for Fair Multi-modal LLMs [59.61512883471714]
  Multi-modal Large Language Models (MLLMs) have dramatically advanced the research field and delivered powerful vision-language understanding capabilities.<n>These models often inherit deep-rooted social biases from their training data, leading to uncomfortable responses with respect to attributes such as race and gender.<n>This paper addresses the issue of social biases in MLLMs by introducing a comprehensive counterfactual dataset with multiple social concepts.
  arXiv  Detail & Related papers  (2024-08-13T02:08:32Z)
• On the steerability of large language models toward data-driven personas [98.9138902560793]
  Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to achieve controllable generation of specific viewpoints using LLMs.
  arXiv  Detail & Related papers  (2023-11-08T19:01:13Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)
• Training Socially Aligned Language Models on Simulated Social Interactions [99.39979111807388]
  Social alignment in AI systems aims to ensure that these models behave according to established societal values. Current language models (LMs) are trained to rigidly replicate their training corpus in isolation. This work presents a novel training paradigm that permits LMs to learn from simulated social interactions.
  arXiv  Detail & Related papers  (2023-05-26T14:17:36Z)

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.