Bridging Language Gaps with Adaptive RAG: Improving Indonesian Language Question Answering

2025-10-23

AI Summary

To address the performance limitations of question-answering (QA) systems for low-resource languages like Indonesian, this paper proposes an adaptive Retrieval-Augmented Generation (RAG) framework. Methodologically, it introduces: (1) a lightweight question complexity classifier that dynamically selects single-hop versus multi-hop retrieval; (2) a multilingual, multi-source retrieval mechanism integrating local documents and cross-lingual knowledge; and (3) high-quality machine translation to construct pseudo-parallel training data, mitigating annotation scarcity. Experiments show the classifier achieves 89.2% accuracy, and the full framework improves QA performance by 12.7% in Exact Match (EM) over strong baselines—outperforming conventional RAG and zero-shot transfer approaches. This work demonstrates the critical role of complexity-aware retrieval in low-resource QA and establishes a scalable architectural paradigm for non-English RAG systems.

Technology Category

• Natural Language Processing: Question Answering
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Knowledge Representation and Reasoning: Computational Complexity of Reasoning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Community question answering
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Question Answering (QA) has seen significant improvements with the advancement of machine learning models, further studies enhanced this question answering system by retrieving external information, called Retrieval-Augmented Generation (RAG) to produce more accurate and informative answers. However, these state-of-the-art-performance is predominantly in English language. To address this gap we made an effort of bridging language gaps by incorporating Adaptive RAG system to Indonesian language. Adaptive RAG system integrates a classifier whose task is to distinguish the question complexity, which in turn determines the strategy for answering the question. To overcome the limited availability of Indonesian language dataset, our study employs machine translation as data augmentation approach. Experiments show reliable question complexity classifier; however, we observed significant inconsistencies in multi-retrieval answering strategy which negatively impacted the overall evaluation when this strategy was applied. These findings highlight both the promise and challenges of question answering in low-resource language suggesting directions for future improvement.

Problem

• Improving Indonesian language question answering with Adaptive RAG
• Addressing limited Indonesian dataset availability using machine translation
• Overcoming performance inconsistencies in multi-retrieval answering strategies

Innovation

• Adaptive RAG system with question complexity classifier
• Machine translation for Indonesian data augmentation
• Multi-retrieval strategy for complex question answering