Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models
This addresses cultural misalignment in LLMs for real-world applications, offering a task-specific solution to improve performance in culturally sensitive domains.
The paper tackles the problem of aligning large language models with culturally sensitive tasks by proposing CultureManager, a pipeline that synthesizes task-aware cultural data and manages multi-culture knowledge with a router, resulting in consistent improvements over baselines across ten national cultures.
Large language models (LLMs) are increasingly deployed in culturally sensitive real-world tasks. However, existing cultural alignment approaches fail to align LLMs' broad cultural values with the specific goals of downstream tasks and suffer from cross-culture interference. We propose CultureManager, a novel pipeline for task-specific cultural alignment. CultureManager synthesizes task-aware cultural data in line with target task formats, grounded in culturally relevant web search results. To prevent conflicts between cultural norms, it manages multi-culture knowledge learned in separate adapters with a culture router that selects the appropriate one to apply. Experiments across ten national cultures and culture-sensitive tasks show consistent improvements over prompt-based and fine-tuning baselines. Our results demonstrate the necessity of task adaptation and modular culture management for effective cultural alignment.