# The Constitutional Coverage Trilemma in AI Governance

arXiv: https://arxiv.org/abs/2609.01275 · HTML: https://mlsanity.com/paper/2609.01275/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [Deliberative Alignment: Reasoning Enables Safer Language Models](https://mlsanity.com/paper/2412.16339/) (2024)
- [The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientation](https://mlsanity.com/paper/2301.01768/) (2023)
- [Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback](https://mlsanity.com/paper/2404.10271/) (2024)

## Abstract (arXiv)

Frontier AI systems function as constitutional institutions: each deployed model encodes an implicit ranking among safety, helpfulness, honesty, autonomy, and equity. We ask whether the supply of frontier constitutional types covers human demand. Combining a paraphrase-controlled audit of the as-shipped default constitutions of 23 frontier LLM archetypes with a pairwise-tradeoff study of 1,649 US participants on the same instrument, we report three facts. Demand is broad: it spans all five values, with the largest constituency under one-third. Supply is narrow and drifting: the 23-archetype hull occupies ~2% of the demand hull under conservative noise-matched estimation (0.10% at full audit precision), no archetype puts helpfulness or autonomy first (37% of users are constitutionally homeless), and across six model families autonomy decreases in 5/6, equity increases in 5/6, and safety increases in 4/6, with monotone within-family version trends (order-permutation p = 0.013) and the autonomy decline concentrated in scenarios where safety is not at stake. The drift's importance is directional: away from a value already undercovered, mechanically worsening the welfare floor for the least-served users. The fix is sparse: a 2-vertex menu eHON, eAUT beats the full 23-archetype frontier by 47% on mean regret (CI [43%, 52%]); three vertex additions cut mean/worst-group regret by up to 81%/64%. We formalize these findings as a budgeted-pluralism trilemma, show the binding regime is empirically realized, and verify the conclusions are robust to distance-based welfare and to degraded routing. The instrument and audit harness are described in full in the appendices.