The Democratic Ontology Deficit: How AI Systems Fail to Represent What Democracy Requires

• URL: http://arxiv.org/abs/2604.03865v1
• Date: Sat, 04 Apr 2026 21:05:31 GMT
• Title: The Democratic Ontology Deficit: How AI Systems Fail to Represent What Democracy Requires
• Abstract summary: This paper identifies and tests the democratic ontology deficit.<n>The model's default ontology is organized under independence rather than civic structure.<n>The deepest deficit is in role: the model's representation of what a person is defaults almost entirely to individual rather than communal identity.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Democratic public life depends on institutions that make roles, responsibilities, relationships, and purposes intelligible as lived orientation. Contemporary AI systems are trained on web-scale corpora and aligned for helpfulness, harmlessness, and honesty, but the representational structure of democratic institutional life has not been treated as an alignment target. This paper identifies and tests the democratic ontology deficit: the structural mismatch between the representational conditions democratic agency requires and the ontology contemporary AI systems are built to learn and reproduce. We apply representation engineering to three instruction-tuned models (Llama-2-13b-chat, Mistral-7B-Instruct-v0.2, and Meta-Llama-3-8B-Instruct), extracting reading vectors for civic reasoning and its four component primitives using contrastive stimuli. The model's default ontology is organized under independence rather than civic structure. The deepest deficit is in role: the model's representation of what a person is defaults almost entirely to individual rather than communal identity. Honesty, measured on the same model at the same layer using the same method, scores 0.707; civic role scores -0.047. The pattern replicates across architectures and training generations. These findings open a concrete research program for civic alignment using the tools the field already possesses.

Related papers

• From Echo Chambers to Epistemic Monoculture: Large Language Models Present Temporally Contingent Partisan Alignments as Knowledge [0.0]
  We present experiments that exploit a model's training cutoff in 2024.<n>We find that the model presents temporally contingent partisan alignments as knowledge, with no mechanism for distinguishing fact from opinion.
  arXiv  Detail & Related papers  (2026-09-07T16:41:56Z)
• A Roadmap to Impactful Pluralistic Alignment Research [43.31026042225045]
  Pluralistic value alignment has emerged as an active research agenda.<n>Yet, there's no public evidence that it has shaped the training or evaluation of the AI systems people actually use.<n>This goes against the primary motivations and goals of pluralistic alignment.
  arXiv  Detail & Related papers  (2026-07-24T13:46:03Z)
• When Agents Evolve, Institutions Follow [52.359340707289114]
  We argue that multi-agent systems built on large language models face the same challenge.<n>Their central problem is not only individual intelligence, but collective organization.<n>We translate seven historical political institutions, spanning four canonical governance patterns, into executable multi-agent architectures.
  arXiv  Detail & Related papers  (2026-04-30T10:30:58Z)
• Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond [209.35045331678043]
  We introduce a "levels x laws" taxonomy organized along two axes.<n>The first defines three capability levels: L1 Predictor, which learns one-step local transition operators; L2 Simulator, which composes them into multi-step, action-conditioned rollouts that respect domain laws; and L3 Evolver, which autonomously revises its own model when predictions fail against new evidence.<n>We synthesize over 400 works and summarize more than 100 representative systems spanning model-based reinforcement learning, video generation, web and GUI agents, multi-agent social simulation, and AI-driven scientific discovery.
  arXiv  Detail & Related papers  (2026-04-24T17:48:47Z)
• Governing Reflective Human-AI Collaboration: A Framework for Epistemic Scaffolding and Traceable Reasoning [0.0]
  This paper proposes a complementary approach in which reasoning is treated as a relational process distributed between human and model.<n>Instead of engineering reasoning solely within models, we frame it as a cognitive protocol that can be structured, measured, and governed using existing systems.
  arXiv  Detail & Related papers  (2026-04-16T11:42:36Z)
• RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark [71.3555284685426]
  We introduce RealUnify, a benchmark designed to evaluate bidirectional capability synergy.<n>RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks.<n>We find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient.
  arXiv  Detail & Related papers  (2025-09-29T15:07:28Z)
• Cognitive Castes: Artificial Intelligence, Epistemic Stratification, and the Dissolution of Democratic Discourse [0.0]
  The argument traces how contemporary AI systems amplify the reasoning capacity of individuals equipped with abstraction, symbolic logic, and adversarial interrogation.<n>The proposed response is not technocratic regulation, nor universal access, but the reconstruction of rational autonomy as a civic mandate.
  arXiv  Detail & Related papers  (2025-07-16T08:46:45Z)
• Cultural Bias in Large Language Models: Evaluating AI Agents through Moral Questionnaires [0.0]
  Large Language Models fail to represent diverse cultural moral frameworks despite their linguistic capabilities.<n>Surprisingly, increased model size doesn't consistently improve cultural representation fidelity.<n>Our results call for more grounded alignment objectives and evaluation metrics to ensure AI systems represent diverse human values.
  arXiv  Detail & Related papers  (2025-07-14T08:59:26Z)
• Aligning AI with Public Values: Deliberation and Decision-Making for Governing Multimodal LLMs in Political Video Analysis [48.14390493099495]
  How AI models should deal with political topics has been discussed, but it remains challenging and requires better governance.<n>This paper examines the governance of large language models through individual and collective deliberation, focusing on politically sensitive videos.
  arXiv  Detail & Related papers  (2024-09-15T03:17:38Z)
• Representation Bias in Political Sample Simulations with Large Language Models [54.48283690603358]
  This study seeks to identify and quantify biases in simulating political samples with Large Language Models. Using the GPT-3.5-Turbo model, we leverage data from the American National Election Studies, German Longitudinal Election Study, Zuobiao dataset, and China Family Panel Studies.
  arXiv  Detail & Related papers  (2024-07-16T05:52:26Z)
• A Roadmap to Pluralistic Alignment [49.29107308098236]
  We propose a roadmap to pluralistic alignment, specifically using language models as a test bed. We identify and formalize three possible ways to define and operationalize pluralism in AI systems. We argue that current alignment techniques may be fundamentally limited for pluralistic AI.
  arXiv  Detail & Related papers  (2024-02-07T18:21:17Z)
• Embedding Democratic Values into Social Media AIs via Societal Objective Functions [13.903836222333977]
  We introduce a method for translating established, vetted social scientific constructs into AI objective functions. We create a democratic attitude model that estimates the extent to which a social media post promotes anti-democratic attitudes. This method presents a novel strategy to draw on social science theory and methods to mitigate societal harms in social media AIs.
  arXiv  Detail & Related papers  (2023-07-26T02:27:24Z)

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.