Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise
Shuai Feng, Wei-Chuang Chan, Srishti Chouhan, Junior Francisco Garcia Ayala, Srujananjali Medicherla, Kyle Clark, and Mingwei Shi

TL;DR
This paper presents a novel soft prompt fine-tuning framework that enables large language models to achieve culturally-sensitive interactions efficiently by dynamically routing queries to specialized cultural experts, significantly improving alignment scores.
Contribution
Introduces a modular soft prompt tuning method for cultural alignment in LLMs, avoiding costly full fine-tuning and enhancing cultural sensitivity and adaptability.
Findings
Alignment scores improved from 0.208 to 0.820
Framework significantly enhances cultural sensitivity
Enables dynamic routing to cultural experts
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsService-Learning and Community Engagement · Evaluation and Performance Assessment
