AI Paper Atlas

Research map / Large language models / Alignment and preferences

CultureRL: Internalizing Cultural Principles in Large Language Models via Norm-Driven Reinforcement Learning

Weixiang Zhao, Haozhen Li, Yanyan Zhao, Haixiao Liu, Biye Li, Ting Liu, Bing Qin

AAAI 2026 · Large language models › Alignment and preferences · approach: Steering and correcting LLM behavior · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add norm-cluster-based reward (cluster-specific norm rules) instead of all norm rules without clustering (ablation)CultureRL-IRQ · WVS (IRQ)1 - JSD: 82.84 -> 86.35Improved
add norm-cluster-based reward (cluster-specific norm rules) instead of all norm rules without clustering (ablation)CultureRL-IRQ · VSM13 (IRQ)Euclidean distance: 77.16 -> 62.24Improved
add norm-cluster-based reward (cluster-specific norm rules) instead of all norm rules without clustering (ablation)CultureRL-IRQ · Content moderation (IRQ)F1: 43.92 -> 49.34Improved
add norm-cluster-based reward (cluster-specific norm rules) instead of all norm rules without clustering (ablation)CultureRL-TUR · WVS (TUR)1 - JSD: 78.50 -> 79.98Improved
add norm-cluster-based reward (cluster-specific norm rules) instead of all norm rules without clustering (ablation)CultureRL-TUR · VSM13 (TUR)Euclidean distance: 129.52 -> 111.25Improved
add norm-cluster-based reward (cluster-specific norm rules) instead of all norm rules without clustering (ablation)CultureRL-TUR · Content moderation (TUR)F1: 50.61 -> 57.37Improved
add norm-cluster-based reward (cluster-specific norm rules) instead of all norm rules without clustering (ablation)CultureRL-USA · WVS (USA)1 - JSD: 76.63 -> 76.72Improved
add norm-cluster-based reward (cluster-specific norm rules) instead of all norm rules without clustering (ablation)CultureRL-USA · VSM13 (USA)Euclidean distance: 173.25 -> 131.40Improved
add norm-cluster-based reward (cluster-specific norm rules) instead of all norm rules without clustering (ablation)CultureRL-USA · Content moderation (USA)F1: 38.61 -> 40.98Improved
use norm-cluster-based reward instead of top-5 retrieved norm rules per sample (ablation)CultureRL-IRQ · WVS (IRQ)1 - JSD: 72.34 -> 86.35Improved
use norm-cluster-based reward instead of top-5 retrieved norm rules per sample (ablation)CultureRL-IRQ · VSM13 (IRQ)Euclidean distance: 155.03 -> 62.24Improved
use norm-cluster-based reward instead of top-5 retrieved norm rules per sample (ablation)CultureRL-IRQ · Content moderation (IRQ)F1: 46.37 -> 49.34Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy