AgriChat: A Multimodal Large Language Model for Agriculture Image Understanding

TL;DR

AgriChat introduces a multimodal large language model tailored for agriculture, utilizing a novel dataset and verification pipeline to enhance accuracy and trustworthiness in agricultural image understanding tasks.

Contribution

The paper presents the V2VK annotation pipeline and the AgriMM benchmark, enabling the development of a specialized MLLM with verified domain knowledge for agriculture.

Findings

AgriChat outperforms other open-source models on agricultural tasks.

The AgriMM benchmark contains over 3,000 classes and 607k VQAs.

Grounding training data in verified literature reduces hallucinations.

Abstract

The deployment of Multimodal Large Language Models (MLLMs) in agriculture is currently stalled by a critical trade-off: the existing literature lacks the large-scale agricultural datasets required for robust model development and evaluation, while current state-of-the-art models lack the verified domain expertise necessary to reason across diverse taxonomies. To address these challenges, we propose the Vision-to-Verified-Knowledge (V2VK) pipeline, a novel generative AI-driven annotation framework that integrates visual captioning with web-augmented scientific retrieval to autonomously generate the AgriMM benchmark, effectively eliminating biological hallucinations by grounding training data in verified phytopathological literature. The AgriMM benchmark contains over 3,000 agricultural classes and more than 607k VQAs spanning multiple tasks, including fine-grained plant species identification, plant disease symptom recognition, crop counting, and ripeness assessment. Leveraging this verifiable data, we present AgriChat, a specialized MLLM that presents broad knowledge across thousands of agricultural classes and provides detailed agricultural assessments with extensive explanations. Extensive evaluation across diverse tasks, datasets, and evaluation conditions reveals both the capabilities and limitations of current agricultural MLLMs, while demonstrating AgriChat's superior performance over other open-source models, including internal and external benchmarks. The results validate that preserving visual detail combined with web-verified knowledge constitutes a reliable pathway toward robust and trustworthy agricultural AI. The code and dataset are publicly available at https://github.com/boudiafA/AgriChat .