Pluralistic Alignment in Large Language Models: Objectives, Human References, and Preference Representations
Pluralistic alignment aims to represent meaningful variation in human preferences rather than collapse heterogeneous judgments into a single target. Yet existing work often mixes three distinct questions: what pluralistic behavior a model should exhibit, whose preferences define the reference, and what evidence is sufficient to demonstrate success. We organize the literature around a two-layer taxonomy. Layer 1 distinguishes representing a range of human-supported viewpoints (Overton Pluralism), adapting faithfully to a specified perspective or preference condition (Steerable Pluralism), and matching the response distribution observed in a target population (Distributional Pluralism). Lay...
| Authors | Meng-Chen Wu, Umesh Bodhwani |
|---|---|
| Primary category | cs.AI |
| Published | 17 October 2026 |
| Last updated at source | 22 October 2026 |
Popularity, last 4 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Recent changes
- 23 Oct 2026 Name: Pluralistic Alignment in Language Models: Objectives, Human References, and Preference Representations → Pluralistic Alignment in Large Language Models: Objectives, Human References, and Preference Representations
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 23 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.