Cost-Efficient Cross-Lingual Retrieval-Augmented Generation for Low-Resource Languages: A Case Study in Bengali Agricultural Advisory
This addresses the language barrier for farmers in developing regions by enabling access to authoritative agricultural knowledge in their local language, though it is incremental as it builds on existing RAG and translation methods.
The paper tackled the problem of providing reliable agricultural advisory in low-resource languages like Bengali by developing a cost-efficient cross-lingual Retrieval-Augmented Generation framework, achieving an average end-to-end latency below 20 seconds with reliable source-grounded responses.
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