{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T06:25:16Z","timestamp":1787034316042,"version":"build-2736575974"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Rapid advances in smart agriculture have highlighted the potential of large language models (LLMs), while practical applications remain limited by privacy risks, high training costs, and hallucinations. Focusing on garlic cultivation, this study proposes a knowledge-graph-enhanced framework that improves domain-specific LLMs through graph-based retrieval.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A hybrid clustering algorithm with intra-cluster multidimensional ranking is employed to identify ten core entity types from garlic-related corpora. Few-shot learning and chain-of-thought prompting are further integrated to optimize entity and relation extraction using Qwen 2.5:32B, leading to the construction of a structured garlic cultivation knowledge graph. The knowledge graph is integrated with LLMs via GraphRAG, while prompt reconstruction strategies are adopted to enrich contextual information and constrain generation, thereby improving domain grounding and reducing hallucinations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental results demonstrate absolute improvements of 13.0, 37.0, and 28.2 percentage points in precision, recall, and F1-score, respectively, for triple extraction compared with the baseline LLM, along with a 37.5 percentage point increase in retrieval-based question-answering accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The proposed approach is interpretable and locally deployable without dependence on commercial APIs, offering a transferable methodological reference for domain-specific knowledge graph construction and intelligent question answering across diverse crop systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpls.2026.1912355","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:37:00Z","timestamp":1787031420000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge-enhanced large language model construction for garlic cultivation using GraphRAG"],"prefix":"10.3389","volume":"17","author":[{"given":"Kai","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Mechanical and Electronic Engineering, Shandong Agricultural University","place":["Tai\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyao","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electronic Engineering, Shandong Agricultural University","place":["Tai\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinkai","family":"Meng","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electronic Engineering, Shandong Agricultural University","place":["Tai\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiacheng","family":"Lv","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electronic Engineering, Shandong Agricultural University","place":["Tai\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojun","family":"Long","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electronic Engineering, Shandong Agricultural University","place":["Tai\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Beijing University of Posts and Telecommunications","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhua","family":"Li","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electronic Engineering, Shandong Agricultural University","place":["Tai\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jialin","family":"Hou","sequence":"additional","affiliation":[{"name":"College of Mechanical and Electronic Engineering, Shandong Agricultural University","place":["Tai\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.18550\/arXiv.2005.14165","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1007\/s10676-024-09802-5","article-title":"Large language models and their big bullshit potential","volume":"26","author":"Fisher","year":"2024","journal-title":"Ethics Inf. Technol."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1702045","article-title":"Garlic-YOLO-DD: a lightweight object detection algorithm for garlic damage detection","volume":"16","author":"Gao","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B4","doi-asserted-by":"publisher","first-page":"112632","DOI":"10.1016\/j.cclet.2026.112632","article-title":"DressingGraphRAG: a domain-specific research assistant integrating GraphRAG and LLMs for wound dressing research","author":"Jiang","year":"2026","journal-title":"Chin. Chem. Lett."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113197","article-title":"Knowledge assimilation: implementing knowledge-guided agricultural large language model","volume":"314","author":"Jiang","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109796","article-title":"A two-stage framework for pig disease knowledge graph fusing","volume":"229","author":"Jiang","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.108924","article-title":"AI for crop production-where can large language models (LLMs) provide substantial value","volume":"221","author":"Kuska","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128614","article-title":"Decoupled semantic graph neural network for knowledge graph embedding","volume":"611","author":"Li","year":"2025","journal-title":"Neurocomputing"},{"key":"B9","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s00521-020-05057-5","article-title":"Domain knowledge graph-based research progress of knowledge representation","volume":"33","author":"Lin","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"B10","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1109\/TFUZZ.2020.2966182","article-title":"Determine the number of unknown targets in open world based on elbow method","volume":"29","author":"Liu","year":"2021","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"B11","first-page":"12","article-title":"Experiment on positive bud rate of garlic planter","volume":"9","author":"Luan","year":"2019","journal-title":"Agric. Eng."},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109398","article-title":"VEG-MMKG: multimodal knowledge graph construction for vegetables based on pre-trained model extraction","volume":"226","author":"Lv","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"B13","doi-asserted-by":"publisher","first-page":"13071","DOI":"10.1007\/s10462-023-10465-9","article-title":"Knowledge graphs: opportunities and challenges","volume":"56","author":"Peng","year":"2023","journal-title":"Artif. Intell. Rev."},{"key":"B14","doi-asserted-by":"publisher","first-page":"26839","DOI":"10.1109\/ACCESS.2024.3365742","article-title":"A review on large language models: architectures, applications, taxonomies, open issues and challenges","volume":"12","author":"Raiaan","year":"2024","journal-title":"IEEE Access"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3390\/math12060929","article-title":"Prompt optimization in large language models","volume":"12","author":"Sabbatella","year":"2024","journal-title":"Mathematics"},{"key":"B16","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1186\/s13007-025-01450-0","article-title":"Recent advances in plant disease detection: challenges and opportunities","volume":"21","author":"Shafay","year":"2025","journal-title":"Plant Methods"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.csi.2025.104005","article-title":"Fields of the future: digital transformation in smart agriculture with large language models and generative AI","volume":"94","author":"Shaikh","year":"2025","journal-title":"Comput. Stand. Interfaces"},{"key":"B18","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s13638-021-01910-w","article-title":"A quantitative discriminant method of elbow point for the optimal number of clusters in clustering algorithm","volume":"2021","author":"Shi","year":"2021","journal-title":"EURASIP J. Wirel. Commun. Netw."},{"key":"B19","doi-asserted-by":"publisher","first-page":"80716","DOI":"10.1109\/ACCESS.2020.29887963","article-title":"Unsupervised K-means clustering algorithm","volume":"8","author":"Sinaga","year":"2020","journal-title":"IEEE Access"},{"key":"B20","doi-asserted-by":"publisher","first-page":"138375","DOI":"10.1109\/ACCESS.2023.3339552","article-title":"Semi-supervised bootstrapped syntax-semantics-based approach for agriculture relation extraction for knowledge graph creation and reasoning","volume":"11","author":"Veena","year":"2023","journal-title":"IEEE Access"},{"key":"B21","doi-asserted-by":"publisher","first-page":"115","DOI":"10.2478\/jaiscr-2025-0007","article-title":"A comprehensive survey of retrieval-augmented large language models for decision making in agriculture: unsolved problems and research opportunities","volume":"15","author":"Vizniuk","year":"2025","journal-title":"J. Artif. Intell. Soft Comput. Res."},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2024.102820","article-title":"Knowledge graph of agricultural engineering technology based on large language model","volume":"85","author":"Wang","year":"2024","journal-title":"Displays"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1482275","article-title":"Research on the construction of a knowledge graph for tomato leaf pests and diseases based on the named entity recognition model","volume":"15","author":"Wang","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B24","doi-asserted-by":"publisher","first-page":"5368","DOI":"10.1021\/acssuschemeng.5c00798","article-title":"LLMs assisted materials development: case of predictive analytics for oxygen evolution reaction catalysts of (oxy)hydroxides","volume":"13","author":"Wei","year":"2025","journal-title":"ACS Sustain. Chem. Eng."},{"key":"B25","doi-asserted-by":"publisher","first-page":"24824","DOI":"10.48550\/arXiv.2201.11903","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process Syst"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.13339","article-title":"Analyzing chain-of-thought prompting in large language models via gradient-based feature attributions","author":"Wu","year":"2023","journal-title":"arXiv"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1696872","article-title":"Crop GraphRAG: pest and disease knowledge base Q&A system for sustainable crop protection","volume":"16","author":"Wu","year":"2026","journal-title":"Front. Plant Sci."},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2024.1434222","article-title":"From laboratory to field: cross-domain few-shot learning for crop disease identification in the field","volume":"15","author":"Yang","year":"2024","journal-title":"Front. Plant Sci."},{"key":"B29","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s13007-022-00866-2","article-title":"A survey of few-shot learning in smart agriculture: developments, applications, and challenges","volume":"18","author":"Yang","year":"2022","journal-title":"Plant Methods"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.15115","article-title":"Qwen2.5 technical report","author":"Yang","year":"2025","journal-title":"arXiv"},{"key":"B31","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s00607-025-01499-8","article-title":"A review on synergizing knowledge graphs and large language models","volume":"107","author":"Yang","year":"2025","journal-title":"Computing"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2025.110218","article-title":"Agricultural large language model for standardized production of distinctive agricultural products","volume":"234","author":"Yi","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3390\/math13040566","article-title":"IPM-AgriGPT: a large language model for pest and disease management with a G-EA framework and agricultural contextual reasoning","volume":"13","author":"Zhang","year":"2025","journal-title":"Mathematics"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture14081359","article-title":"Implementation of large language models and agricultural knowledge graphs for efficient plant disease detection","volume":"14","author":"Zhao","year":"2024","journal-title":"Agriculture"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2025.106179","article-title":"Automating construction contract review using knowledge graph-enhanced large language models","volume":"175","author":"Zheng","year":"2025","journal-title":"Autom. Constr."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.3389\/fpls.2025.1579355","article-title":"Harnessing large vision and language models in agriculture: a review","volume":"16","author":"Zhu","year":"2025","journal-title":"Front. Plant Sci."},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109824","article-title":"Potato disease detection and prevention using multimodal AI and large language model","volume":"229","author":"Zhu","year":"2025","journal-title":"Comput. Electron. Agric."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1912355\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:37:02Z","timestamp":1787031422000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1912355\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":37,"alternative-id":["10.3389\/fpls.2026.1912355"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1912355","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]},"article-number":"1912355"}}