Taxonomy / Steerable persona pluralism / Describing the persona in the prompt

Describing the persona in the prompt

Whose side the model takes is set by words at inference — a system message stating what the user values, a persona description to role-play, or simply who the asker says they are. The method paper here trains a model on 192k combinations of stated values for exactly this purpose: to make the text channel reliable for value profiles never seen in training, so adding a persona costs a sentence rather than a retraining run. The rest of the strand measures that channel — how far prompting can actually shift a model's behavior as steering effort rises, how faithfully a model role-plays a described persona when human judges check it, and the finding that the channel fires unbidden, since models swing their stated politics toward whoever they infer is asking.

The method, against Steerable persona pluralism

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.

Plural normative orders

PartialNot claimed

Definition · John Griffiths, What Is Legal Pluralism? (1986)

Different communities' norms are genuinely in force at once — not one official rulebook plus tolerated deviations, but multiple living systems of rules side by side.

Analysis

The three benchmarks take plurality seriously enough to make it the measured quantity — coverage of the range of defensible views, steerability to a named persona, fidelity to a named community's norms — and OvertonBench's finding that models cover only about a third of the range is the map's first hard number on the question. But the orders are supplied by the benchmark designer: census-derived synthetic personas, curated question sets, named clusters. Measuring plurality is not putting any community's norms in force.

A conflict rule between orders

AbsentNot claimed · out of scope

Definition · Conflict-of-laws tradition

When two communities' norms disagree about the same case, something must say which governs — and why. That stated rule is what separates real pluralism from mere fragmentation into disconnected groups.

Analysis

Every persona, viewpoint and community is scored on its own. No item in any of the three sets is a case on which two of them have a competing claim, so the question a conflict rule answers is never put.

A shared floor

AbsentNot claimed · out of scope

Definition · J. S. Mill, On Liberty (1859)

Accommodation of group differences has a limit stated in advance — classically Mill's harm principle: your practices are your business until they harm others. Without an enforced floor, pluralism collapses into "each group gets whatever it wants".

Analysis

Nothing in the scoring marks a position as out of bounds. OvertonBench rewards covering the range of defensible views, but the range is elicited from a representative human sample rather than bounded by any stated principle — so what is defensible is whatever people said, which is the opposite of a floor fixed in advance.

Concept Analysis: Newly Introduced

A number for how plural a model is

Added

Pluralist political theory argues about how much difference a system should accommodate. Formalizing Overton pluralism as set coverage produces an actual figure — current models carry roughly a third to two-fifths of the range of defensible views — which turns the argument into a measurement, at the cost of taking the range of defensible views as whatever a survey sample supplied.

Papers