AgriRegion: Region-Aware Retrieval for High-Fidelity Agricultural Advice

TL;DR

AgriRegion is a specialized retrieval-augmented framework that enhances agricultural advice accuracy by incorporating geospatial data and local knowledge, reducing hallucinations and increasing trustworthiness in region-specific contexts.

Contribution

It introduces a novel geospatial-aware retrieval method and a benchmark dataset for region-specific agricultural advice, improving factual accuracy over general LLMs.

Findings

Reduces hallucinations by 10-20% compared to state-of-the-art models.

Improves trust scores in region-specific agricultural advice.

Demonstrates effectiveness across 12 agricultural subfields.

Abstract

Large Language Models (LLMs) have demonstrated significant potential in democratizing access to information. However, in the domain of agriculture, general-purpose models frequently suffer from contextual hallucination, which provides non-factual advice or answers are scientifically sound in one region but disastrous in another due to variations in soil, climate, and local regulations. We introduce AgriRegion, a Retrieval-Augmented Generation (RAG) framework designed specifically for high-fidelity, region-aware agricultural advisory. Unlike standard RAG approaches that rely solely on semantic similarity, AgriRegion incorporates a geospatial metadata injection layer and a region-prioritized re-ranking mechanism. By restricting the knowledge base to verified local agricultural extension services and enforcing geo-spatial constraints during retrieval, AgriRegion ensures that the advice regarding planting schedules, pest control, and fertilization is locally accurate. We create a novel benchmark dataset, AgriRegion-Eval, which comprises 160 domain-specific questions across 12 agricultural subfields. Experiments demonstrate that AgriRegion reduces hallucinations by 10-20% compared to state-of-the-art LLMs systems and significantly improves trust scores according to a comprehensive evaluation.