@inproceedings{mahmood-etal-2026-agrichain,
title = "{A}gri{C}hain: Visually-Grounded Expert-Verified Reasoning for Interpretable Agricultural Vision{--}Language Models",
author = "Mahmood, Hazza and
Yu, Yongqiang and
Anwer, Rao",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.177/",
doi = "10.63317/2bv5k9hnduop",
pages = "2268--2276",
abstract = "Accurate and interpretable plant disease diagnosis remains a key challenge for vision{--}language models in real agricultural settings. We present AgriChain, a new dataset of around 11,000 expert-curated leaf images covering a wide range of crops and diseases. Each image is paired with a disease label, a calibrated confidence score, and an expert-verified chain-of-thought explanation. Draft rationales were first generated by GPT-4o and then refined by a professional agricultural engineer using standard descriptors such as lesion color, margin, and distribution. Using these data, we fine-tune the open vision{--}language model Qwen-2.5-VL-3B to jointly identify diseases and explain its reasoning in a way that mirrors expert thinking. On a 1,000-image test set, our model reaches 73.1{\%} accuracy and produces explanations that align closely with human expertise. These results show that expert-verified reasoning supervision enhances both performance and interpretability, bringing us closer to transparent and trustworthy AI tools for sustainable agriculture.To support reproducibility and further research, the dataset and code are publicly available at \url{https://github.com/hazzanabeel12-netizen/agrichain}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mahmood-etal-2026-agrichain">
<titleInfo>
<title>AgriChain: Visually-Grounded Expert-Verified Reasoning for Interpretable Agricultural Vision–Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hazza</namePart>
<namePart type="family">Mahmood</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongqiang</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rao</namePart>
<namePart type="family">Anwer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Accurate and interpretable plant disease diagnosis remains a key challenge for vision–language models in real agricultural settings. We present AgriChain, a new dataset of around 11,000 expert-curated leaf images covering a wide range of crops and diseases. Each image is paired with a disease label, a calibrated confidence score, and an expert-verified chain-of-thought explanation. Draft rationales were first generated by GPT-4o and then refined by a professional agricultural engineer using standard descriptors such as lesion color, margin, and distribution. Using these data, we fine-tune the open vision–language model Qwen-2.5-VL-3B to jointly identify diseases and explain its reasoning in a way that mirrors expert thinking. On a 1,000-image test set, our model reaches 73.1% accuracy and produces explanations that align closely with human expertise. These results show that expert-verified reasoning supervision enhances both performance and interpretability, bringing us closer to transparent and trustworthy AI tools for sustainable agriculture.To support reproducibility and further research, the dataset and code are publicly available at https://github.com/hazzanabeel12-netizen/agrichain.</abstract>
<identifier type="citekey">mahmood-etal-2026-agrichain</identifier>
<identifier type="doi">10.63317/2bv5k9hnduop</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.177/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>2268</start>
<end>2276</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AgriChain: Visually-Grounded Expert-Verified Reasoning for Interpretable Agricultural Vision–Language Models
%A Mahmood, Hazza
%A Yu, Yongqiang
%A Anwer, Rao
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F mahmood-etal-2026-agrichain
%X Accurate and interpretable plant disease diagnosis remains a key challenge for vision–language models in real agricultural settings. We present AgriChain, a new dataset of around 11,000 expert-curated leaf images covering a wide range of crops and diseases. Each image is paired with a disease label, a calibrated confidence score, and an expert-verified chain-of-thought explanation. Draft rationales were first generated by GPT-4o and then refined by a professional agricultural engineer using standard descriptors such as lesion color, margin, and distribution. Using these data, we fine-tune the open vision–language model Qwen-2.5-VL-3B to jointly identify diseases and explain its reasoning in a way that mirrors expert thinking. On a 1,000-image test set, our model reaches 73.1% accuracy and produces explanations that align closely with human expertise. These results show that expert-verified reasoning supervision enhances both performance and interpretability, bringing us closer to transparent and trustworthy AI tools for sustainable agriculture.To support reproducibility and further research, the dataset and code are publicly available at https://github.com/hazzanabeel12-netizen/agrichain.
%R 10.63317/2bv5k9hnduop
%U https://aclanthology.org/2026.lrec-1.177/
%U https://doi.org/10.63317/2bv5k9hnduop
%P 2268-2276
Markdown (Informal)
[AgriChain: Visually-Grounded Expert-Verified Reasoning for Interpretable Agricultural Vision–Language Models](https://aclanthology.org/2026.lrec-1.177/) (Mahmood et al., LREC 2026)
ACL