Taxonomy / Deliberative aggregation / Revising cases and principles against each other

Revising cases and principles against each other

Here the collective answer is not a tally at all. Concrete judgments about particular cases and candidate general principles are adjusted against each other until the two cohere — modeled formally under measurable account, systematicity and faithfulness criteria, read as a description of what constitutional AI already does, and shown to be the same search as coherence-driven self-improvement. Attached to the machinery are the arguments for why the target should be justified reasons rather than counts: that preferences do not represent values, and that alignment should be settled by the claims people can fairly make on each other.

The method, against Deliberative aggregation

Scroll the diagram sideways to see all of it.

Concept Analysis: Theoretical Foundations

Each concept is read twice: whether the approach carries it, and whether the approach's own sources claim it. A concept that is absent and was never claimed is a gap in the field rather than a failure of the work, and is marked out of scope.

Deliberation, Not Tallying

AbsentNot claimed · out of scope

Definition · Jürgen Habermas, Between Facts and Norms (1992)

This concept locates legitimacy in the exchange of reasons among equals: participants justify their views to each other, free of coercion, and remain able to change their minds. Counting votes or averaging preferences does not produce it, because the reasoning is what does the work.

Analysis

The revision runs between one reasoner's judgments and principles. It takes place within a single person rather than among parties.

General Will vs. Sum of Preferences

AbsentNot claimed · out of scope

Definition · Jean-Jacques Rousseau, The Social Contract (1762)

This distinction separates what is good for a public in common from the sum of what its members privately want. Aggregating private wants, however fairly, does not produce the former, since the two can and often do diverge.

Analysis

The method is not addressed to a public's common interest. It is a coherence procedure for a single agent's morality.

Veil of Ignorance

AbsentNot claimed · out of scope

Definition · John Rawls, A Theory of Justice (1971)

This device requires that rules be chosen without knowledge of which position the chooser will occupy under them, e.g., rich or poor, majority or minority. Not knowing generally pushes the chooser to protect the worst-off position, since it may turn out to be their own.

Analysis

No form of positional ignorance appears anywhere in the method.

Reasonable Rejection

AbsentNot claimed · out of scope

Definition · T. M. Scanlon, What We Owe to Each Other (1998)

This test holds a principle justified only if no individual could reasonably reject it, and it is applied person by person rather than in aggregate. One sufficiently strong objection therefore outweighs many mild preferences, which is the case averaging handles wrongly.

Analysis

The test is coherence with the reasoner's own considered judgments rather than justifiability to anyone else.

Concept Analysis: Newly Introduced

A stopping condition for value revision

Added

These works formalize when revision should stop, i.e., the point at which judgments and principles cohere and no further change is called for. The process is specified but is not coupled to any training or inference loop, so nothing runs it.

Papers

Self-Improvement as Coherence Optimization: A Theoretical Account

Tianyi Qiu et al., Jan 2026

arXiv:2601.135661 citationMethodPartial

Shows that debate, bootstrapping and internal-coherence maximization are all instances of one thing — searching for the most compressible, jointly predictable mapping from context to behavior — and proves that this is equivalent to description-length regularization.

Argued for, not built

These make the case for this approach, or sketch a design for it, but leave nothing built and tested behind.

Beyond Preferences in AI Alignment

Tan Zhi-Xuan et al., Aug 2024

arXiv:2408.1698471 citationsProposalGap

Names the "preferentist" commitments underlying mainstream alignment — that preferences represent values, that rationality is preference satisfaction, and that systems should be aligned to preferences — and sets out conceptual alternatives to each.

Wide Reflective Equilibrium in LLM Alignment: Bridging Moral Epistemology and AI Safety

Matthew Brophy, May 2025

arXiv:2506.004150 citationsProposalPartial

Argues that the method of wide reflective equilibrium is the right description of what Constitutional AI already does, and proposes concrete ways to make its revision loop more legitimate.

A matter of principle? AI alignment as the fair treatment of claims

Iason Gabriel & Geoff Keeling, 2025

doi:10.1007/s11098-025-02300-416 citationsProposalGap

Precedent from outside AI

Work from law, political theory or another discipline that supplies the tradition this approach is read against.

Making Reflective Equilibrium Precise: A Formal Model

Claus Beisbart et al., 2021

doi:10.3998/ergo.1152PrecedentPartial

Builds an explicit formal model of reflective equilibrium in which commitments and principles are adjusted against each other under measurable account, systematicity and faithfulness criteria.