Cost-Efficient Cross-Lingual Retrieval-Augmented Generation for Low-Resource Languages: A Case Study in Bengali Agricultural Advisory

TL;DR

This paper introduces a cost-effective cross-lingual RAG system for Bengali agricultural advice, translating queries to English, retrieving info from manuals, and translating responses back, enabling accessible, factual, low-resource language support.

Contribution

It presents a novel translation-centric, open-source RAG framework tailored for low-resource languages, combining translation, domain-specific keyword injection, and dense retrieval for practical deployment.

Findings

Reliable, source-grounded responses achieved

System operates with low latency (<20 seconds)

Effective rejection of out-of-domain queries

Abstract

Access to reliable agricultural advisory remains limited in many developing regions due to a persistent language barrier: authoritative agricultural manuals are predominantly written in English, while farmers primarily communicate in low-resource local languages such as Bengali. Although recent advances in Large Language Models (LLMs) enable natural language interaction, direct generation in low-resource languages often exhibits poor fluency and factual inconsistency, while cloud-based solutions remain cost-prohibitive. This paper presents a cost-efficient, cross-lingual Retrieval-Augmented Generation (RAG) framework for Bengali agricultural advisory that emphasizes factual grounding and practical deployability. The proposed system adopts a translation-centric architecture in which Bengali user queries are translated into English, enriched through domain-specific keyword injection to align colloquial farmer terminology with scientific nomenclature, and answered via dense vector retrieval over a curated corpus of English agricultural manuals (FAO, IRRI). The generated English response is subsequently translated back into Bengali to ensure accessibility. The system is implemented entirely using open-source models and operates on consumer-grade hardware without reliance on paid APIs. Experimental evaluation demonstrates reliable source-grounded responses, robust rejection of out-of-domain queries, and an average end-to-end latency below 20 seconds. The results indicate that cross-lingual retrieval combined with controlled translation offers a practical and scalable solution for agricultural knowledge access in low-resource language settings