AgriPestDatabase-v1.0: A Structured Insect Dataset for Training Agricultural Large Language Model

2026-03-24

AI Summary

This study addresses the scarcity of high-quality annotated data and limited expert support in agricultural pest management in rural areas by constructing a structured textual dataset of pests and generating semantic-oriented question-answer pairs grounded in expert-validated knowledge. These resources are used to fine-tune lightweight large language models via efficient domain adaptation using LoRA, targeting deployment on edge devices. Experimental results demonstrate that the fine-tuned Mistral-7B model achieves an 88.9% pass rate and a semantic similarity score of 0.865 on domain-specific QA tasks, significantly outperforming Qwen2.5-7B and LLaMA3.1-8B. To the best of our knowledge, this work presents the first edge-deployable agricultural domain language model tailored for in-field applications.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Natural Language Processing: Question Answering
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Agricultural pest management increasingly relies on timely and accurate access to expert knowledge, yet high quality labeled data and continuous expert support remain limited, particularly for farmers operating in rural regions with unstable/no internet connectivity. At the same time, the rapid growth of AI and LLMs has created new opportunities to deliver practical decision support tools directly to end users in agriculture through compact and deployable systems. This work addresses (i) generating a structured insect information dataset, and (ii) adapting a lightweight LLM model ($\leq$ 7B) by fine tuning it for edge device uses in agricultural pest management. The textual data collection was done by reviewing and collecting information from available pest databases and published manuscripts on nine selected pest species. These structured reports were then reviewed and validated by a domain expert. From these reports, we constructed Q/A pairs to support model training and evaluation. A LoRA-based fine-tuning approach was applied to multiple lightweight LLMs and evaluated. Initial evaluation shows that Mistral 7B achieves an 88.9\% pass rate on the domain-specific Q/A task, substantially outperforming Qwen 2.5 7B (63.9\%), and LLaMA 3.1 8B (58.7\%). Notably, Mistral demonstrates higher semantic alignment (embedding similarity: 0.865) despite lower lexical overlap (BLEU: 0.097), indicating that semantic understanding and robust reasoning are more predictive of task success than surface-level conformity in specialized domains. By combining expert organized data, well-structured Q/A pairs, semantic quality control, and efficient model adaptation, this work contributes towards providing support for farmer facing agricultural decision support tools and demonstrates the feasibility of deploying compact, high-performing language models for practical field-level pest management guidance.

Problem

• agricultural pest management
• labeled data scarcity
• expert knowledge access
• rural connectivity
• decision support

Innovation

• structured pest dataset
• lightweight LLM
• LoRA fine-tuning
• edge deployment
• semantic alignment