AgriChain Visually Grounded Expert Verified Reasoning for Interpretable Agricultural Vision Language Models
This work addresses the problem of trustworthy AI for plant disease diagnosis in agriculture, offering an incremental improvement through expert-verified reasoning supervision.
The paper tackles the challenge of accurate and interpretable plant disease diagnosis in agriculture by introducing AgriChain, a dataset of 11,000 expert-curated leaf images with disease labels, confidence scores, and expert-verified chain-of-thought rationales, and fine-tuning Qwen2.5-VL-3B on it to achieve 73.1% top-1 accuracy, outperforming strong baselines like Gemini and GPT-4o Mini.
Accurate and interpretable plant disease diagnosis remains a major challenge for vision-language models (VLMs) in real-world agriculture. We introduce AgriChain, a dataset of approximately 11,000 expert-curated leaf images spanning diverse crops and pathologies, each paired with (i) a disease label, (ii) a calibrated confidence score (High/Medium/Low), and (iii) an expert-verified chain-of-thought (CoT) rationale. Draft explanations were first generated by GPT-4o and then verified by a professional agricultural engineer using standardized descriptors (e.g., lesion color, margin, and distribution). We fine-tune Qwen2.5-VL-3B on AgriChain, resulting in a specialized model termed AgriChain-VL3B, to jointly predict diseases and generate visually grounded reasoning. On a 1,000-image test set, our CoT-supervised model achieves 73.1% top-1 accuracy (macro F1 = 0.466; weighted F1 = 0.655), outperforming strong baselines including Gemini 1.5 Flash, Gemini 2.5 Pro, and GPT-4o Mini. The generated explanations align closely with expert reasoning, consistently referencing key visual cues. These findings demonstrate that expert-verified reasoning supervision significantly enhances both accuracy and interpretability, bridging the gap between generic multimodal models and human expertise, and advancing trustworthy, globally deployable AI for sustainable agriculture. The dataset and code are publicly available at: https://github.com/hazzanabeel12-netizen/agrichain