AgriRegion: Region-Aware Retrieval for High-Fidelity Agricultural Advice
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918243126476800 |
|---|---|
| author | Fanuel, Mesafint Mahmoud, Mahmoud Nabil Marshal, Crystal Cook Lakhotia, Vishal Dari, Biswanath Roy, Kaushik Zhang, Shaohu |
| author_facet | Fanuel, Mesafint Mahmoud, Mahmoud Nabil Marshal, Crystal Cook Lakhotia, Vishal Dari, Biswanath Roy, Kaushik Zhang, Shaohu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_10114 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgriRegion: Region-Aware Retrieval for High-Fidelity Agricultural Advice Fanuel, Mesafint Mahmoud, Mahmoud Nabil Marshal, Crystal Cook Lakhotia, Vishal Dari, Biswanath Roy, Kaushik Zhang, Shaohu Artificial Intelligence 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. |
| title | AgriRegion: Region-Aware Retrieval for High-Fidelity Agricultural Advice |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2512.10114 |