Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Adams, Jadie, Hu, Brian, Veenhuis, Emily, Joy, David, Ravichandran, Bharadwaj, Bray, Aaron, Hoogs, Anthony, Basharat, Arslan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912532922368000
author Adams, Jadie
Hu, Brian
Veenhuis, Emily
Joy, David
Ravichandran, Bharadwaj
Bray, Aaron
Hoogs, Anthony
Basharat, Arslan
author_facet Adams, Jadie
Hu, Brian
Veenhuis, Emily
Joy, David
Ravichandran, Bharadwaj
Bray, Aaron
Hoogs, Anthony
Basharat, Arslan
contents Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average. Pluralistic alignment instead seeks to capture diverse user preferences across a set of attributes, moving beyond just helpfulness and harmlessness. Toward this end, we propose a steerable pluralistic model based on few-shot comparative regression that can adapt to individual user preferences. Our approach leverages in-context learning and reasoning, grounded in a set of fine-grained attributes, to compare response options and make aligned choices. To evaluate our algorithm, we also propose two new steerable pluralistic benchmarks by adapting the Moral Integrity Corpus (MIC) and the HelpSteer2 datasets, demonstrating the applicability of our approach to value-aligned decision-making and reward modeling, respectively. Our few-shot comparative regression approach is interpretable and compatible with different attributes and LLMs, while outperforming multiple baseline and state-of-the-art methods. Our work provides new insights and research directions in pluralistic alignment, enabling a more fair and representative use of LLMs and advancing the state-of-the-art in ethical AI.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08509
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression
Adams, Jadie
Hu, Brian
Veenhuis, Emily
Joy, David
Ravichandran, Bharadwaj
Bray, Aaron
Hoogs, Anthony
Basharat, Arslan
Computation and Language
Artificial Intelligence
Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average. Pluralistic alignment instead seeks to capture diverse user preferences across a set of attributes, moving beyond just helpfulness and harmlessness. Toward this end, we propose a steerable pluralistic model based on few-shot comparative regression that can adapt to individual user preferences. Our approach leverages in-context learning and reasoning, grounded in a set of fine-grained attributes, to compare response options and make aligned choices. To evaluate our algorithm, we also propose two new steerable pluralistic benchmarks by adapting the Moral Integrity Corpus (MIC) and the HelpSteer2 datasets, demonstrating the applicability of our approach to value-aligned decision-making and reward modeling, respectively. Our few-shot comparative regression approach is interpretable and compatible with different attributes and LLMs, while outperforming multiple baseline and state-of-the-art methods. Our work provides new insights and research directions in pluralistic alignment, enabling a more fair and representative use of LLMs and advancing the state-of-the-art in ethical AI.
title Steerable Pluralism: Pluralistic Alignment via Few-Shot Comparative Regression
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2508.08509