来自多方海岸的低语：通过协作式文化专长实现文化对齐
Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise
AI总结：
针对LLM文化对齐成本高、理解不足的问题，提出基于向量化提示调优的软提示微调框架，动态路由查询至文化专家委员会，将对齐分数从0.208提升至0.820。
摘要：
将大型语言模型（LLMs）集成到全球应用中，需要有效的文化对齐以实现有意义且具有文化敏感性的交互。当前的LLMs通常缺乏多元文化语境所需的细致理解，而适应这些模型通常涉及成本高昂的全量微调。为解决这一问题，我们提出了一种新颖的软提示微调框架，能够实现高效且模块化的文化对齐。该方法利用向量化提示调优，动态将查询路由至一个由文化专业化“专家”LLM配置组成的委员会，这些配置通过优化软提示嵌入创建，无需更改基础模型的参数。大量实验表明，该框架显著增强了文化敏感性和适应性，将对齐分数从0.208提升至0.820，为具有文化意识的LLM部署提供了稳健的解决方案。本研究为后续探索增强文化覆盖和动态专家适应铺平了道路，这对于在全球化互联世界中实现具备深刻细致理解的自主AI至关重要。
英文摘要：
The integration of large language models (LLMs) into global applications necessitates effective cultural alignment for meaningful and culturally-sensitive interactions. Current LLMs often lack the nuanced understanding required for diverse cultural contexts, and adapting them typically involves costly full fine-tuning. To address this, we introduce a novel soft prompt fine-tuning framework that enables efficient and modular cultural alignment. Our method utilizes vectorized prompt tuning to dynamically route queries to a committee of culturally specialized 'expert' LLM configurations, created by optimizing soft prompt embeddings without altering the base model's parameters. Extensive experiments demonstrate that our framework significantly enhances cultural sensitivity and adaptability, improving alignment scores from 0.208 to 0.820, offering a robust solution for culturally-aware LLM deployment. This research paves the way for subsequent investigations into enhanced cultural coverage and dynamic expert adaptation, crucial for realizing autonomous AI with deeply nuanced understanding in a globally interconnected world.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
