Leveraging Retrieval-Augmented Generation for Culturally Inclusive Hakka Chatbots: Design Insights and User Perceptions
Chen-Chi Chang, Han-Pi Chang, Hung-Shin Lee

TL;DR
This paper presents a Retrieval-Augmented Generation (RAG) based chatbot designed to promote Taiwanese Hakka culture by providing culturally accurate and contextually rich responses, enhancing user engagement and cultural preservation.
Contribution
It introduces a novel RAG-enhanced chatbot that integrates cultural data to improve accuracy and cultural resonance in Hakka language and traditions.
Findings
Improved user satisfaction and engagement with the chatbot.
Effective handling of complex, culturally specific inquiries.
Potential for cultural preservation through AI-driven digital platforms.
Abstract
In an era where cultural preservation is increasingly intertwined with technological innovation, this study introduces a groundbreaking approach to promoting and safeguarding the rich heritage of Taiwanese Hakka culture through the development of a Retrieval-Augmented Generation (RAG)-enhanced chatbot. Traditional large language models (LLMs), while powerful, often fall short in delivering accurate and contextually rich responses, particularly in culturally specific domains. By integrating external databases with generative AI models, RAG technology bridges this gap, empowering chatbots to not only provide precise answers but also resonate deeply with the cultural nuances that are crucial for authentic interactions. This study delves into the intricate process of augmenting the chatbot's knowledge base with targeted cultural data, specifically curated to reflect the unique aspects of…
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
TopicsAI in Service Interactions
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Adam · Linear Layer · Dropout · Byte Pair Encoding · Layer Normalization · Residual Connection · Linear Warmup With Linear Decay · Attention Is All You Need · Dense Connections
