PaperScope
LIVE · 2026-09-29 05:40 UTC

CRISP: Cultural Reward Modeling for Implicit Situated Propriety

Zekun Yuan, Yangfan Ye, Baohang Li, Shuaibo Zhao, Zekun Zhou, Ziming Li, Qichen Hong, Kun Chen, Xiaocheng Feng

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.34345 v1
Category
Submitted
2026-09-28

Abstract

As large language models (LLMs) are increasingly deployed across countries and regions, the ability to recognize and respond appropriately to diverse cultural contexts becomes increasingly important. However, existing research has largely focused on cultural knowledge or tasks with predefined response spaces, while open-ended culturally situated behavior remains comparatively underexplored. In this work, we introduce CRISP-RM, a culturally situated reward model that assigns rewards according to cultural appropriateness in open-ended social scenarios. During policy optimization, we further introduce Norm Grounding Supervision (NGS), providing guidance that enhances the policy's sensitivity to relevant cultural norms. To construct culturally situated data, we employ a collaborative multi-agent framework that instantiates implicit cultural norms into diverse social scenarios and further curate NormCompass as a dedicated testbed. We conduct comprehensive experiments to evaluate the effectiveness of CRISP-RM in both reward modeling and policy optimization. Best-of-\(N\) experiments show that CRISP-RM consistently outperforms strong general reward models. During GRPO policy optimization, CRISP-RM generally improves culturally situated behavior, while incorporating NGS yields further gains. Further analyses demonstrate the advantages of CRISP-RM in distinguishing culturally appropriate behavior beyond superficial fluency and politeness, while NGS provides complementary gains during policy optimization by improving norm grounding.

Comment: 27 pages, 6 figrues

arXiv abs page · PDF · same-day batch