AgriChain：基于视觉的专家验证推理用于可解释的农业视觉语言模型
AgriChain Visually Grounded Expert Verified Reasoning for Interpretable Agricultural Vision Language Models
AI总结：
本文提出AgriChain数据集，通过专家验证的推理链提升农业视觉语言模型的准确性和可解释性，实验表明其在植物病害诊断中优于多个基线模型。
摘要：
准确且可解释的植物疾病诊断仍然是视觉-语言模型（VLMs）在现实农业中的主要挑战。我们介绍了AgriChain，一个包含约11,000张专家整理的叶部图像的数据集，涵盖多种作物和病害，每张图像均配以（i）疾病标签，（ii）校准的置信度分数（高/中/低），以及（iii）专家验证的推理链（CoT）。初步解释由GPT-4o生成，随后由专业农业工程师使用标准化描述符（如病变颜色、边缘和分布）验证。我们在AgriChain上微调Qwen2.5-VL-3B，得到专门模型AgriChain-VL3B，用于联合预测疾病并生成视觉基础的推理。在1,000张图像的测试集上，我们的CoT监督模型达到73.1%的top-1准确率（宏F1=0.466；加权F1=0.655），优于Gemini 1.5 Flash、Gemini 2.5 Pro和GPT-4o Mini等强基线模型。生成的解释与专家推理高度一致，持续引用关键视觉线索。这些发现表明，专家验证的推理监督显著提高了准确性和可解释性，弥合了通用多模态模型与人类专业知识之间的差距，并推进了可信赖、全球部署的AI用于可持续农业。数据集和代码可在：https://github.com/hazzanabeel12-netizen/agrichain 公开获取。
英文摘要：
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
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
