Saved in:
Bibliographic Details
Main Authors: Lin, Jiayu, Wei, Zhongyu
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.13669
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915740002549760
author Lin, Jiayu
Wei, Zhongyu
author_facet Lin, Jiayu
Wei, Zhongyu
contents Large language models (LLMs) alignment ensures model behaviors reflect human value. Existing alignment strategies primarily follow two paths: one assumes a universal value set for a unified goal (i.e., one-size-fits-all), while the other treats every individual as unique to customize models (i.e., individual-level). However, assuming a monolithic value space marginalizes minority norms, while tailoring individual models is prohibitively expensive. Recognizing that human society is organized into social clusters with high intra-group value alignment, we propose community-level alignment as a "middle ground". Practically, we introduce CommunityBench, the first large-scale benchmark for community-level alignment evaluation, featuring four tasks grounded in Common Identity and Common Bond theory. With CommunityBench, we conduct a comprehensive evaluation of various foundation models on CommunityBench, revealing that current LLMs exhibit limited capacity to model community-specific preferences. Furthermore, we investigate the potential of community-level alignment in facilitating individual modeling, providing a promising direction for scalable and pluralistic alignment.
format Preprint
id arxiv_https___arxiv_org_abs_2601_13669
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CommunityBench: Benchmarking Community-Level Alignment across Diverse Groups and Tasks
Lin, Jiayu
Wei, Zhongyu
Computation and Language
Large language models (LLMs) alignment ensures model behaviors reflect human value. Existing alignment strategies primarily follow two paths: one assumes a universal value set for a unified goal (i.e., one-size-fits-all), while the other treats every individual as unique to customize models (i.e., individual-level). However, assuming a monolithic value space marginalizes minority norms, while tailoring individual models is prohibitively expensive. Recognizing that human society is organized into social clusters with high intra-group value alignment, we propose community-level alignment as a "middle ground". Practically, we introduce CommunityBench, the first large-scale benchmark for community-level alignment evaluation, featuring four tasks grounded in Common Identity and Common Bond theory. With CommunityBench, we conduct a comprehensive evaluation of various foundation models on CommunityBench, revealing that current LLMs exhibit limited capacity to model community-specific preferences. Furthermore, we investigate the potential of community-level alignment in facilitating individual modeling, providing a promising direction for scalable and pluralistic alignment.
title CommunityBench: Benchmarking Community-Level Alignment across Diverse Groups and Tasks
topic Computation and Language
url https://arxiv.org/abs/2601.13669