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

Source: [AgriRegion: Region-Aware Retrieval for High-Fidelity Agricultural Advice](<https://www.sota2.com/research/paper/693ba1936cfd488761a552de>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-12-13T05:02:27.858Z

Authors: Mesafint Fanuel, Mahmoud Nabil Mahmoud, Crystal Cook Marshal, Vishal Lakhotia, Biswanath Dari, Kaushik Roy, Shaohu Zhang

Published: 2025-12-10T22:06:41.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Question Answering on AgriRegion-Eval 160 questions (test)](<https://www.sota2.com/research/sota/question-answering-on-agriregion-eval-160-questions-test.md>): Question Answering; AgriRegion-Eval 160 questions (test); EM: 76.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2512.10114>)

[PDF](<https://arxiv.org/pdf/2512.10114.pdf>)