Towards Comprehensive Vietnamese Retrieval-Augmented Generation and Large Language Models

2024/03/03 by Nguyen Quang Đuc, Le Hai Son, Duc, Nguyen Quang +9
Computer Science · #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2403.01616

Abstract

This paper presents our contributions towards advancing the state of Vietnamese language understanding and generation through the development and dissemination of open datasets and pre-trained models for Vietnamese Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs).

Related

• Crossing Linguistic Horizons: Finetuning and Comprehensive Evaluation of Vietnamese Large Language Models
• Vi-Mistral-X: Building a Vietnamese Language Model with Advanced Continual Pre-training
• LaVy: Vietnamese Multimodal Large Language Model
• PhoBERT: Pre-trained language models for Vietnamese
• Multi-dimensional data refining strategy for effective fine-tuning LLMs