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

TL;DR

This paper introduces an Adaptive RAG system tailored for Indonesian question answering, utilizing question complexity classification and machine translation for data augmentation, highlighting both potential and challenges in low-resource language QA.

Contribution

It presents a novel Adaptive RAG approach for Indonesian QA, integrating question complexity classification and data augmentation to address low-resource challenges.

Findings

Reliable question complexity classifier developed

Inconsistencies found in multi-retrieval answering strategy

Challenges identified in applying RAG to low-resource languages

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.