cs.AINov 10, 2026

Living constitutions: Participatory alignment for sovereign foundation models

Authors: Stine Lyngsø Beltoft, Jonas Vistrup, Peter Schneider-Kamp, Lukas Galke Poech

Organizations: University of Southern Denmark

Abstract

In Constitutional AI, a plain-text "constitution" encodes values and gets incorporated into a model via post-training. However, the procedure for creating such a constitution poses significant challenges: who contributes, who decides which norms are included, and to what extent must the process be participatory or democratic? These challenges can be paralyzing. Yet, we argue that taking action is essential: without a deliberate constitution, sovereign models would risk misalignment or default to norms set by frontier model providers. We propose treating the development of a constitution as an evolving, participatory process akin to citizen science, iteratively drafted, tested, and refined. We therefore formulate five desirable principles: iterative, modular, justifiable, positional, and legitimate. We further argue that such a document must remain responsive not only over time but across the people it governs, and propose that provisions be marked as settled, contested, or underdetermined, so that durable disagreement is recorded in the constitution rather than resolved away. Empirically, we show via agent-based modelling that proposed process for maintaining living constitutions is robust against 50% bad actors among citizens - assuming a share of 75% participants with good intent in the deliberative body. This indicates that the proposed process tolerates a substantial share of adversarial participants.

Figures & tables

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Jun 29, 2026

Open Problems in Constitutional Preference Reconstruction

Pairwise preference data is widely used for training and evaluating language models (e.g., RLHF), but each datapoint records a choice, not the rationale behind it. Methods such as Inverse Constitutional AI (ICAI) attempt to improve interpretability by compressing datasets into short ``constitutions'' of natural-language principles. We argue this framing is under-specified: a flat list of principles is not yet an executable decision rule because it leaves principle composition implicit. We use the pairwise setting as a testbed to empirically characterize three open problems in constitutional methods. First, principle quality is hard to measure: coverage and accuracy are useful but incomplete proxies for end-to-end reconstruction. Second, composition is ambiguous: holding principles fixed, different executors (LLM judge versus majority vote) agree only 73%73\% of the time. Third, constitutions differ between LLMs: cross-model vote agreement is 73%73\%, whereas intra-model agreement is 81%81\%. Across PRISM, AlpacaEval, and Chatbot Arena, we show that principle refinement (ICAI+) may be a first step towards ameliorating these problems: inter-executor agreement rises to 78%78\%, and transparent executors match LLM judge accuracy (66%66\% vs.\ 67%67\%). Our results highlight that constitutions should be evaluated as constitution--executor systems, with implications for LLMs-as-a-judge broadly.
May 13, 2026

Constitutional Governance in Metric Spaces

Computational social choice and algorithmic decision theory offer rich aggregation theory but no end-to-end process for egalitarian self-governance: aggregation, deliberation, amendment, and consensus are each considered in isolation, with key metric-space aggregators being NP-hard. Here, we propose constitutional governance in metric spaces, integrating these stages into a protocol for constitutional governance. A community's legal corpus comprises its laws together with a constitution, each being a point in a metric space, with the constitution specifying the supermajority threshold required to amend it. Members vote to amend the legal corpus by proposing their ideal points, followed by rounds of submitting public proposals carrying supermajority public support; a polynomial-time aggregation rule scores each proposal, and a supported proposal whose score is positive and maximal for two rounds is adopted; if none is found the status quo is retained. Public proposals can be sourced from deliberation, vote aggregation, or AI mediation. With Constitutional Consensus, a community can run the constitutional governance protocol on members' personal computing devices (e.g., smartphones), achieving digital sovereignty. By drawing on metric-space aggregation, reality-aware social choice, supermajority amendment, constitutional consensus, deliberative coalition formation, and AI mediation, we provide a comprehensive framework for the constitutional governance of digital communities and organisations.
Jun 13, 2026

Constitutional Value Potentials: reading and steering internal priority margins in language models

Safety evaluations test a policy on prompts that omit the incentive information deployment supplies: a commission, a performance score, a dashboard naming which action pays best. We measure what that omission hides. In MoneyWorld, a synthetic workplace environment, we train five instruction-tuned models from three families with RL on non-safety tasks in which a visible payoff signal identifies a rewarded shortcut that sacrifices task quality. We then freeze each policy, present held-out safety conflicts, and change only the displayed signal. Each menu contains one compliant action and three violations. We report three findings, with rates for Qwen2.5-14B-Instruct. (i) Payoff signals control frozen safety choices: unsafe choice is 100% when the signal names an unsafe option and 0% when it is hidden or names the safe one. Hidden- and random-signal training controls stay at or below 0.3%, and the switch reproduces on all five bases. Numerical payouts reproduce it under sampled-action rewards, reaching 98.6% unsafe choice at a $1 advantage. (ii) Payoff identification and unsafe choice separate under a training-menu intervention: training on task-completing actions at the same payouts retains 99.8% identification while reducing unsafe choice to 7.9% at matched update budgets. Payoff-reading competence alone does not explain transfer. (iii) The switch does not reproduce in executed retail customer-service tasks using the same frozen adapters. In MoneyWorld, omitting incentive information conceals unsafe choices that appear when the same policy sees which action pays best.