CPJ: Explainable Agricultural Pest Diagnosis via Caption-Prompt-Judge with LLM-Judged Refinement

• URL: http://arxiv.org/abs/2512.24947v1
• Date: Wed, 31 Dec 2025 16:21:31 GMT
• Title: CPJ: Explainable Agricultural Pest Diagnosis via Caption-Prompt-Judge with LLM-Judged Refinement
• Abstract summary: We propose Caption--Prompt--Judge (CPJ), a framework that enhances Agri-Pest VQA through structured, interpretable image captions.<n>CPJ employs large vision-language models to generate multi-angle captions, refined iteratively via an LLM-as-Judge module.<n>The framework provides transparent, evidence-based reasoning, advancing robust and explainable agricultural diagnosis without fine-tuning.
• Score: 17.863109076374727
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate and interpretable crop disease diagnosis is essential for agricultural decision-making, yet existing methods often rely on costly supervised fine-tuning and perform poorly under domain shifts. We propose Caption--Prompt--Judge (CPJ), a training-free few-shot framework that enhances Agri-Pest VQA through structured, interpretable image captions. CPJ employs large vision-language models to generate multi-angle captions, refined iteratively via an LLM-as-Judge module, which then inform a dual-answer VQA process for both recognition and management responses. Evaluated on CDDMBench, CPJ significantly improves performance: using GPT-5-mini captions, GPT-5-Nano achieves \textbf{+22.7} pp in disease classification and \textbf{+19.5} points in QA score over no-caption baselines. The framework provides transparent, evidence-based reasoning, advancing robust and explainable agricultural diagnosis without fine-tuning. Our code and data are publicly available at: https://github.com/CPJ-Agricultural/CPJ-Agricultural-Diagnosis.

Related papers

• Agri-CPJ: A Training-Free Explainable Framework for Agricultural Pest Diagnosis Using Caption-Prompt-Judge and LLM-as-a-Judge [40.23111543895404]
  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.<n>Two candidate responses are then generated from complementary viewpoints, and an LLM judge selects the stronger one based on domain-specific criteria.<n>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.
  arXiv  Detail & Related papers  (2026-04-26T13:33:45Z)
• Job Skill Extraction via LLM-Centric Multi-Module Framework [51.37063712967151]
  We present SRICL, an LLM-centric framework that combines semantic retrieval, in-context learning, and supervised fine-tuning.<n>On six public span-labeled corpora of job-ad sentences, SRICL achieves substantial STRICT-F1 improvements over GPT-3.5 prompting baselines and sharply reduces invalid tags and hallucinated spans.
  arXiv  Detail & Related papers  (2026-04-23T10:46:07Z)
• A Hybrid Knowledge-Grounded Framework for Safety and Traceability in Prescription Verification [7.782616091483888]
  We introduce PharmGraph-Auditor, a novel system designed for safe and evidence-grounded prescription auditing.<n>The core of our system is a trustworthy Hybrid Pharmaceutical Knowledge Base (HPKB), implemented under the Virtual Knowledge Graph paradigm.<n>For auditing, we introduce the KB-grounded Chain of Verification (CoV), a new reasoning paradigm that transforms the LLM from an unreliable generator into a transparent reasoning engine.
  arXiv  Detail & Related papers  (2026-03-11T15:35:55Z)
• Graph-Augmented Reasoning with Large Language Models for Tobacco Pest and Disease Management [9.759725097042656]
  This paper proposes a graph-augmented reasoning framework for tobacco pest and disease management.<n>We construct a domain-specific knowledge graph and retrieve query-relevant subgraphs to provide relational evidence during answer generation.
  arXiv  Detail & Related papers  (2026-02-02T18:29:52Z)
• ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval [64.14282916266998]
  Composed Image Retrieval aims to retrieve target images based on a hybrid query comprising a reference image and a modification text.<n>We propose ReCALL, a model-agnostic framework that follows a diagnose-generate-refine pipeline.<n>Experiments on CIRR and FashionIQ show that ReCALL consistently recalibrates degraded capabilities and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-02T04:52:54Z)
• Agri-R1: Empowering Generalizable Agricultural Reasoning in Vision-Language Models with Reinforcement Learning [22.34625628938106]
  We propose textbfAgri-R1, a reasoning-enhanced large model for agriculture.<n>Our framework high-quality reasoning data generation via vision-language synthesis and LLM-based filtering.<n>We show a +23.2% relative gain in disease recognition accuracy, +33.3% in agricultural knowledge QA, and a +26.10-point improvement in cross-domain generalization.
  arXiv  Detail & Related papers  (2026-01-08T07:34:37Z)
• ReAG: Reasoning-Augmented Generation for Knowledge-based Visual Question Answering [54.72902502486611]
  ReAG is a Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages.<n>ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence.
  arXiv  Detail & Related papers  (2025-11-27T19:01:02Z)
• Adaptive Diagnostic Reasoning Framework for Pathology with Multimodal Large Language Models [34.28963665009494]
  We present RECAP-PATH, an interpretable framework that establishes a self-learning paradigm.<n>It shifts off-the-shelf multimodal large language models from passive pattern recognition to evidence-linked diagnostic reasoning.<n>This self-learning approach requires only small labeled sets and no white-box access or weight updates to generate cancer diagnoses.
  arXiv  Detail & Related papers  (2025-11-15T03:06:59Z)
• Agro-Consensus: Semantic Self-Consistency in Vision-Language Models for Crop Disease Management in Developing Countries [2.2727733134290813]
  Agricultural disease management in developing countries faces significant challenges due to limited access to expert plant pathologists.<n>This work introduces a cost-effective self-consistency framework to improve vision-language model (VLM) reliability for agricultural image captioning.
  arXiv  Detail & Related papers  (2025-10-11T19:41:07Z)
• CANDLE: A Cross-Modal Agentic Knowledge Distillation Framework for Interpretable Sarcopenia Diagnosis [3.0245458192729466]
  CANDLE mitigates the interpretability-performance trade-off, enhances predictive accuracy, and preserves high decision consistency.<n>The framework offers a scalable approach to knowledge assetization of TML models, enabling interpretable, reproducible, and clinically aligned decision support in sarcopenia and potentially broader medical domains.
  arXiv  Detail & Related papers  (2025-07-26T15:50:08Z)
• Self-Consistency in Vision-Language Models for Precision Agriculture: Multi-Response Consensus for Crop Disease Management [0.0]
  This work presents a domain-aware framework for agricultural image processing that combines prompt-based expert evaluation with self-consistency mechanisms.<n>We introduce two key innovations: (1) a prompt-based evaluation protocol that configures a language model as an expert plant pathologist for scalable assessment of image analysis outputs, and (2) a cosine-consistency self-voting mechanism that generates multiple candidate responses from agricultural images.<n>Our approach improves diagnostic accuracy from 82.2% to 87.8%, symptom analysis from 38.9% to 52.2%, and treatment recommendation from 27.8% to 43.3
  arXiv  Detail & Related papers  (2025-07-08T18:32:21Z)
• Silence is Not Consensus: Disrupting Agreement Bias in Multi-Agent LLMs via Catfish Agent for Clinical Decision Making [80.94208848596215]
  We present a new concept called Catfish Agent, a role-specialized LLM designed to inject structured dissent and counter silent agreement.<n>Inspired by the catfish effect'' in organizational psychology, the Catfish Agent is designed to challenge emerging consensus to stimulate deeper reasoning.
  arXiv  Detail & Related papers  (2025-05-27T17:59:50Z)
• AGIR: Assessing 3D Gait Impairment with Reasoning based on LLMs [0.0]
  gait impairment plays an important role in early diagnosis, disease monitoring, and treatment evaluation for neurodegenerative diseases.<n>Recent deep learning-based approaches have consistently improved classification accuracies, but they often lack interpretability.<n>We introduce AGIR, a novel pipeline consisting of a pre-trained VQ-VAE motion tokenizer and a Large Language Model (LLM) fine-tuned over pairs of motion tokens.
  arXiv  Detail & Related papers  (2025-03-23T17:12:16Z)
• LlaMADRS: Prompting Large Language Models for Interview-Based Depression Assessment [75.44934940580112]
  This study introduces LlaMADRS, a novel framework leveraging open-source Large Language Models (LLMs) to automate depression severity assessment.<n>We employ a zero-shot prompting strategy with carefully designed cues to guide the model in interpreting and scoring transcribed clinical interviews.<n>Our approach, tested on 236 real-world interviews, demonstrates strong correlations with clinician assessments.
  arXiv  Detail & Related papers  (2025-01-07T08:49:04Z)
• Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage [50.84150600032693]
  Multimodal large language models (MLLMs) excel at generating highly detailed captions but often produce hallucinations.<n>We propose a multiagent approach that leverages LLM-MLLM collaboration to correct given captions.<n>Our proposed method significantly enhances the factual accuracy of captions, even improving those generated by GPT-4V.
  arXiv  Detail & Related papers  (2024-12-20T01:37:22Z)
• MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models [49.765466293296186]
  Recent progress in Medical Large Vision-Language Models (Med-LVLMs) has opened up new possibilities for interactive diagnostic tools.<n>Med-LVLMs often suffer from factual hallucination, which can lead to incorrect diagnoses.<n>We propose a versatile multimodal RAG system, MMed-RAG, designed to enhance the factuality of Med-LVLMs.
  arXiv  Detail & Related papers  (2024-10-16T23:03:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.