{"id":"https://openalex.org/W4413356567","doi":"https://doi.org/10.1186/s40537-025-01236-0","title":"Chat-rgie: precision extraction of rice germplasm data using large language models and prompt engineering","display_name":"Chat-rgie: precision extraction of rice germplasm data using large language models and prompt engineering","publication_year":2025,"publication_date":"2025-08-20","ids":{"openalex":"https://openalex.org/W4413356567","doi":"https://doi.org/10.1186/s40537-025-01236-0"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-025-01236-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01236-0","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01236-0","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01236-0","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yijin Wei","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093981","display_name":"Agricultural Information Institute","ror":"https://ror.org/00q62zf58","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210093981","https://openalex.org/I4210127390","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210120962","display_name":"Chinese Academy of Agricultural Engineering","ror":"https://ror.org/02ag25v06","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210120962","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yijin Wei","raw_affiliation_strings":["Agriculture Information Institution, Chinese Academy of Agricultural Sciences, No. 12 South Street, Haidian district, Beijing, 100081, China","National Agriculture Science Data Center, No. 12 South Street, Haidian district, Beijing, 100081, China"],"affiliations":[{"raw_affiliation_string":"Agriculture Information Institution, Chinese Academy of Agricultural Sciences, No. 12 South Street, Haidian district, Beijing, 100081, China","institution_ids":["https://openalex.org/I4210120962","https://openalex.org/I4210093981"]},{"raw_affiliation_string":"National Agriculture Science Data Center, No. 12 South Street, Haidian district, Beijing, 100081, China","institution_ids":["https://openalex.org/I4210156423"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002536740","display_name":"Jingchao Fan","orcid":"https://orcid.org/0000-0003-2969-4117"},"institutions":[{"id":"https://openalex.org/I4210093981","display_name":"Agricultural Information Institute","ror":"https://ror.org/00q62zf58","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210093981","https://openalex.org/I4210127390","https://openalex.org/I4210138501","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210120962","display_name":"Chinese Academy of Agricultural Engineering","ror":"https://ror.org/02ag25v06","country_code":"CN","type":"government","lineage":["https://openalex.org/I4210120962","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]},{"id":"https://openalex.org/I4210156423","display_name":"National Engineering Research Center for Information Technology in Agriculture","ror":"https://ror.org/04c3j3t84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210156423"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingchao Fan","raw_affiliation_strings":["Agriculture Information Institution, Chinese Academy of Agricultural Sciences, No. 12 South Street, Haidian district, Beijing, 100081, China","National Agriculture Science Data Center, No. 12 South Street, Haidian district, Beijing, 100081, China"],"affiliations":[{"raw_affiliation_string":"Agriculture Information Institution, Chinese Academy of Agricultural Sciences, No. 12 South Street, Haidian district, Beijing, 100081, China","institution_ids":["https://openalex.org/I4210120962","https://openalex.org/I4210093981"]},{"raw_affiliation_string":"National Agriculture Science Data Center, No. 12 South Street, Haidian district, Beijing, 100081, China","institution_ids":["https://openalex.org/I4210156423"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210093981","https://openalex.org/I4210120962","https://openalex.org/I4210156423"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":0.7244,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73557484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"12","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9419999718666077,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8185291886329651},{"id":"https://openalex.org/keywords/germplasm","display_name":"Germplasm","score":0.6297928094863892},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.6265383958816528},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.532965898513794},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.49246177077293396},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3878690004348755},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3607628345489502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35092779994010925},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.2731423079967499},{"id":"https://openalex.org/keywords/botany","display_name":"Botany","score":0.10270416736602783},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.06690007448196411}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185291886329651},{"id":"https://openalex.org/C2777461220","wikidata":"https://www.wikidata.org/wiki/Q589029","display_name":"Germplasm","level":2,"score":0.6297928094863892},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.6265383958816528},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.532965898513794},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.49246177077293396},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3878690004348755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3607628345489502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35092779994010925},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2731423079967499},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.10270416736602783},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.06690007448196411},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-025-01236-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01236-0","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01236-0","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cba99ebd50694f8aaec09bc1daeffec4","is_oa":true,"landing_page_url":"https://doaj.org/article/cba99ebd50694f8aaec09bc1daeffec4","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 12, Iss 1, Pp 1-38 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-025-01236-0","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-025-01236-0","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-025-01236-0","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/2","display_name":"Zero hunger","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G2699045012","display_name":null,"funder_award_id":"CAAS-ASTIP","funder_id":"https://openalex.org/F4320323155","funder_display_name":"Chinese Academy of Agricultural Sciences"},{"id":"https://openalex.org/G3399831935","display_name":null,"funder_award_id":"CAAS-ASTIP","funder_id":"https://openalex.org/F4320335848","funder_display_name":"Agricultural Science and Technology Innovation Program"},{"id":"https://openalex.org/G6892687160","display_name":null,"funder_award_id":"ASTIP","funder_id":"https://openalex.org/F4320323155","funder_display_name":"Chinese Academy of Agricultural Sciences"}],"funders":[{"id":"https://openalex.org/F4320323155","display_name":"Chinese Academy of Agricultural Sciences","ror":"https://ror.org/0313jb750"},{"id":"https://openalex.org/F4320335848","display_name":"Agricultural Science and Technology Innovation Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413356567.pdf","grobid_xml":"https://content.openalex.org/works/W4413356567.grobid-xml"},"referenced_works_count":75,"referenced_works":["https://openalex.org/W1682403713","https://openalex.org/W1988902793","https://openalex.org/W2034921015","https://openalex.org/W2035806597","https://openalex.org/W2105594594","https://openalex.org/W2114891756","https://openalex.org/W2139212933","https://openalex.org/W2147880316","https://openalex.org/W2523785361","https://openalex.org/W2560939934","https://openalex.org/W2743151379","https://openalex.org/W2766362701","https://openalex.org/W2890680318","https://openalex.org/W2936166854","https://openalex.org/W2946609015","https://openalex.org/W2950772678","https://openalex.org/W2970119519","https://openalex.org/W2970771982","https://openalex.org/W2992302948","https://openalex.org/W2999645992","https://openalex.org/W3008287297","https://openalex.org/W3022530152","https://openalex.org/W3026048580","https://openalex.org/W3094582681","https://openalex.org/W3100221827","https://openalex.org/W3100452049","https://openalex.org/W3101498587","https://openalex.org/W3127365350","https://openalex.org/W3153451655","https://openalex.org/W3170403598","https://openalex.org/W3176540255","https://openalex.org/W3198659451","https://openalex.org/W3200122731","https://openalex.org/W3205068155","https://openalex.org/W4200155180","https://openalex.org/W4207080468","https://openalex.org/W4221143046","https://openalex.org/W4224909481","https://openalex.org/W4225378608","https://openalex.org/W4225409008","https://openalex.org/W4226278401","https://openalex.org/W4280555259","https://openalex.org/W4281476575","https://openalex.org/W4281617541","https://openalex.org/W4281982434","https://openalex.org/W4283074682","https://openalex.org/W4307139584","https://openalex.org/W4308760226","https://openalex.org/W4311553886","https://openalex.org/W4322718191","https://openalex.org/W4382246105","https://openalex.org/W4384662964","https://openalex.org/W4384918448","https://openalex.org/W4385570391","https://openalex.org/W4385571157","https://openalex.org/W4386002638","https://openalex.org/W4386501105","https://openalex.org/W4387257042","https://openalex.org/W4387338911","https://openalex.org/W4389523706","https://openalex.org/W4389523957","https://openalex.org/W4389524317","https://openalex.org/W4389686182","https://openalex.org/W4392002118","https://openalex.org/W4392376454","https://openalex.org/W4392637287","https://openalex.org/W4392669753","https://openalex.org/W4393160302","https://openalex.org/W4396667188","https://openalex.org/W4398765347","https://openalex.org/W4401483049","https://openalex.org/W6778883912","https://openalex.org/W6803096969","https://openalex.org/W6811340617","https://openalex.org/W6847076894"],"related_works":["https://openalex.org/W2351833475","https://openalex.org/W2390522107","https://openalex.org/W2359194509","https://openalex.org/W2384861711","https://openalex.org/W981080659","https://openalex.org/W2354876815","https://openalex.org/W2382822286","https://openalex.org/W2233210418","https://openalex.org/W2377087328","https://openalex.org/W2379595614"],"abstract_inverted_index":{"Varietal":[0],"improvement":[1],"is":[2,227,245,252],"a":[3,10,27,32,56,144,169,178],"key":[4],"aspect":[5],"of":[6,12,68,128,140,157,185,196,265],"breeding,":[7],"and":[8,45,89,96,104,110,115,165,198,236],"as":[9,71,73],"result":[11],"this":[13],"work,":[14],"crop":[15],"varietal":[16],"data":[17,35,53,82,91,120,134,213],"becomes":[18],"more":[19,22,242],"complicated,":[20],"requiring":[21],"resources":[23],"to":[24,49,64,78,149,151,181,246,254,278],"extract.":[25],"As":[26],"result,":[28],"we":[29,174,210,216],"developed":[30],"Chat-RGIE,":[31,95],"rice":[33,51],"germplasm":[34,52],"extraction":[36,54,83,92,121,135,214],"strategy":[37],"based":[38],"on":[39,94,191],"conversational":[40],"large":[41,146],"language":[42],"models":[43],"(LLM)":[44],"cue":[46],"word":[47],"engineering,":[48],"achieve":[50],"in":[55,107,118,159,200,205,248,268,272],"ZERO-shot":[57],"manner.":[58],"The":[59],"technique":[60],"employs":[61],"multi-response":[62],"voting":[63],"limit":[65],"the":[66,80,97,126,129,132,138,155,160,183,189,201,212,225,230,234,237,239,241,266,269,276],"chance":[67],"phantom":[69],"appearances,":[70],"well":[72],"an":[74,222],"additional":[75],"calibration":[76],"component":[77],"choose":[79],"best":[81],"findings.":[84],"We":[85,260],"performed":[86],"performance":[87,108],"evaluation":[88,93],"real-life":[90,119],"scheme":[98],"obtained":[99],"0.9102":[100],"precision,":[101,112],"0.9941":[102],"recall,":[103,114],"0.9554":[105],"accuracy":[106,117],"evaluation,":[109,122],"0.6351":[111],"1.0":[113],"0.8225":[116],"which":[123,251],"completely":[124],"proved":[125],"effectiveness":[127],"scheme.":[130],"Furthermore,":[131,173,208],"well-designed":[133],"procedure":[136],"mitigates":[137],"likelihood":[139],"potential":[141,277],"bias":[142],"from":[143],"single":[145],"model":[147],"leading":[148],"hallucinations":[150,158],"some":[152,264],"extent,":[153],"with":[154,168,194,221],"incidence":[156],"two":[161,202],"evaluations":[162],"being":[163],"0.0015":[164],"0.005,":[166],"respectively,":[167],"very":[170],"minor":[171],"influence.":[172],"employed":[175],"Restraint":[176],"Rate,":[177],"statistic":[179],"used":[180],"quantify":[182],"degree":[184],"limits":[186],"placed":[187],"by":[188,229,233],"prompt":[190],"LLM":[192,226,281],"replies,":[193],"values":[195],"0.9265":[197],"0.911":[199],"evaluations,":[203],"resulting":[204],"normative":[206],"responses.":[207],"when":[209,219,258],"examined":[211],"results,":[215],"discovered":[217],"that":[218,263],"confronted":[220],"unanswerable":[223],"answer,":[224],"affected":[228],"stress":[231],"provided":[232],"prompt,":[235],"higher":[238],"stress,":[240],"likely":[243],"it":[244],"engage":[247],"constraint-violating":[249],"behavior,":[250],"similar":[253],"what":[255],"humans":[256],"do":[257],"stressed.":[259],"therefore":[261],"believe":[262],"countermeasures":[267],"human":[270],"behavior":[271],"question":[273],"also":[274],"have":[275],"help":[279],"improve":[280],"performance.":[282]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}