Taxonomy / Steerable persona pluralism / Collecting preferences from real people without pooling them
This strand changes the data rather than the model: recruit representative samples of real people, then keep every rating tied to the person who gave it and to what they said they valued, instead of averaging raters into one anonymous signal. Two large studies do it — 1,500 participants from 75 countries whose demographics and stated preferences are mapped onto their feedback in 8,011 live conversations, and a five-country study of 15,000 people releasing 233,319 multilingual comparisons built by prompting for candidate answers that pull in opposite directions. Both report the finding that motivates the whole regime: people vary far more in what they want than today's models' answers do, so pluralism absent from the training signal cannot be steered for later.
Scroll the diagram sideways to see all of it.
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.
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
Behavior genuinely varies per user or group — plurality of a fine-grained sort. But "order" overstates it: what varies is service to individuals, not communities maintaining norm systems of their own.
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
Personalizing per user means conflicts between users' norms never meet in a single case — they are avoided by partition, not resolved by rule. The tradition's central question goes unasked.
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
The limits of personalization are argued carefully — Mill's harm principle, Rawlsian stability — but in prose. The philosophy does the limiting work in the paper, not in the system: no implemented constraint enforces the floor. The bounds are described, not built.
No method has been built here yet — this approach rests entirely on what follows.
Primary documents and shared infrastructure this approach works from or produces, rather than studies of them.
arXiv:2404.16019ResourceBuilt
Maps the demographics and stated preferences of 1,500 participants from 75 countries onto their actual feedback in 8,011 live conversations with 21 models, so a rating can be traced back to who gave it and what they said they valued.
arXiv:2507.09650ResourceBuilt
Runs a preference study with representative samples from five countries (N=15,000), finds that people vary far more in what they want than the responses of 21 state-of-the-art models do, and releases Community Alignment, a multilingual multi-turn dataset of 233,319 comparisons built by prompting for candidate answers that pull in opposite directions.