Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Wentao, Zhang, Qi, Xu, Mingkun, You, Mu, Shen, Henghua, He, Zhongzhi, Jin, Keyan, Wong, Derek F., Fang, Tao
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.23701
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911623336165376
author Zhang, Wentao
Zhang, Qi
Xu, Mingkun
You, Mu
Shen, Henghua
He, Zhongzhi
Jin, Keyan
Wong, Derek F.
Fang, Tao
author_facet Zhang, Wentao
Zhang, Qi
Xu, Mingkun
You, Mu
Shen, Henghua
He, Zhongzhi
Jin, Keyan
Wong, Derek F.
Fang, Tao
contents Crop disease diagnosis from field photographs faces two recurring problems: models that score well on benchmarks frequently hallucinate species names, and when predictions are correct, the reasoning behind them is typically inaccessible to the practitioner. This paper describes Agri-CPJ (Caption-Prompt-Judge), a training-free few-shot framework in which a large vision-language model first generates a structured morphological caption, iteratively refined through multi-dimensional quality gating, before any diagnostic question is answered. Two candidate responses are then generated from complementary viewpoints, and an LLM judge selects the stronger one based on domain-specific criteria. Caption refinement is the component with the largest individual impact: ablations confirm that skipping it consistently degrades downstream accuracy across both models tested. On CDDMBench, pairing GPT-5-Nano with GPT-5-mini-generated captions yields \textbf{+22.7} pp in disease classification and \textbf{+19.5} points in QA score over no-caption baselines. Evaluated without modification on AgMMU-MCQs, GPT-5-Nano reached 77.84\% and Qwen-VL-Chat reached 64.54\%, placing them at or above most open-source models of comparable scale despite the format shift from open-ended to multiple-choice. The structured caption and judge rationale together constitute a readable audit trail: a practitioner who disagrees with a diagnosis can identify the specific caption observation that was incorrect. Code and data are publicly available https://github.com/CPJ-Agricultural/CPJ-Agricultural-Diagnosis
format Preprint
id arxiv_https___arxiv_org_abs_2604_23701
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge
Zhang, Wentao
Zhang, Qi
Xu, Mingkun
You, Mu
Shen, Henghua
He, Zhongzhi
Jin, Keyan
Wong, Derek F.
Fang, Tao
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Crop disease diagnosis from field photographs faces two recurring problems: models that score well on benchmarks frequently hallucinate species names, and when predictions are correct, the reasoning behind them is typically inaccessible to the practitioner. This paper describes Agri-CPJ (Caption-Prompt-Judge), a training-free few-shot framework in which a large vision-language model first generates a structured morphological caption, iteratively refined through multi-dimensional quality gating, before any diagnostic question is answered. Two candidate responses are then generated from complementary viewpoints, and an LLM judge selects the stronger one based on domain-specific criteria. Caption refinement is the component with the largest individual impact: ablations confirm that skipping it consistently degrades downstream accuracy across both models tested. On CDDMBench, pairing GPT-5-Nano with GPT-5-mini-generated captions yields \textbf{+22.7} pp in disease classification and \textbf{+19.5} points in QA score over no-caption baselines. Evaluated without modification on AgMMU-MCQs, GPT-5-Nano reached 77.84\% and Qwen-VL-Chat reached 64.54\%, placing them at or above most open-source models of comparable scale despite the format shift from open-ended to multiple-choice. The structured caption and judge rationale together constitute a readable audit trail: a practitioner who disagrees with a diagnosis can identify the specific caption observation that was incorrect. Code and data are publicly available https://github.com/CPJ-Agricultural/CPJ-Agricultural-Diagnosis
title Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2604.23701