{"id":"https://openalex.org/W4407128583","doi":"https://doi.org/10.48550/arxiv.2502.01059","title":"Knowledge Synthesis of Photosynthesis Research Using a Large Language Model","display_name":"Knowledge Synthesis of Photosynthesis Research Using a Large Language Model","publication_year":2025,"publication_date":"2025-02-03","ids":{"openalex":"https://openalex.org/W4407128583","doi":"https://doi.org/10.48550/arxiv.2502.01059"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2502.01059","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01059","pdf_url":"https://arxiv.org/pdf/2502.01059","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2502.01059","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051536395","display_name":"Seungri Yoon","orcid":"https://orcid.org/0000-0002-6961-9675","observed_orcids":["https://orcid.org/0000-0002-6961-9675"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoon, Seungri","raw_affiliation_strings":["Department of Agriculture, Forestry and Bioresources , Seoul National University , Seoul 08826 , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Agriculture, Forestry and Bioresources , Seoul National University , Seoul 08826 , Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116144069","display_name":"Woosang Jeon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeon, Woosang","raw_affiliation_strings":["Department of Biosystems Engineering , Seoul National University , Seoul 08826 , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biosystems Engineering , Seoul National University , Seoul 08826 , Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Choi, Sanghyeok","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Choi, Sanghyeok","raw_affiliation_strings":["Department of Biosystems Engineering , Seoul National University , Seoul 08826 , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biosystems Engineering , Seoul National University , Seoul 08826 , Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707034","display_name":"Taehyeong Kim","orcid":"https://orcid.org/0000-0002-1862-9208","observed_orcids":["https://orcid.org/0000-0002-1862-9208"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kim, Taehyeong","raw_affiliation_strings":["Department of Biosystems Engineering , Seoul National University , Seoul 08826 , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biosystems Engineering , Seoul National University , Seoul 08826 , Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028248443","display_name":"Tae In Ahn","orcid":"https://orcid.org/0000-0001-5939-7450","observed_orcids":["https://orcid.org/0000-0001-5939-7450"]},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ahn, Tae In","raw_affiliation_strings":["Department of Agriculture, Forestry and Bioresources , Seoul National University , Seoul 08826 , Republic of Korea","Research Institute of Agriculture and Life Sciences , Seoul National University , Seoul 08826 , Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Agriculture, Forestry and Bioresources , Seoul National University , Seoul 08826 , Republic of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Research Institute of Agriculture and Life Sciences , Seoul National University , Seoul 08826 , Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.2572999894618988,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.2572999894618988,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13904","display_name":"Artificial Intelligence Applications","score":0.12929999828338623,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.09790000319480896,"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/photosynthesis-research","display_name":"photosynthesis research","score":0.7409999966621399},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9200000166893005},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.8600000143051147},{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.9890000224113464},{"id":"https://openalex.org/keywords/prompt-optimization","display_name":"prompt optimization","score":0.9120000004768372},{"id":"https://openalex.org/keywords/research-assistants","display_name":"research assistants","score":0.7630000114440918},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.6570000052452087},{"id":"https://openalex.org/keywords/research-gap-identification","display_name":"research gap identification","score":0.7850000262260437},{"id":"https://openalex.org/keywords/scientific-writing","display_name":"scientific writing","score":0.6100000143051147},{"id":"https://openalex.org/keywords/vector-databases","display_name":"vector databases","score":0.5989999771118164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5319310426712036},{"id":"https://openalex.org/C183688256","wikidata":"https://www.wikidata.org/wiki/Q11982","display_name":"Photosynthesis","level":2,"score":0.48758047819137573},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3644856810569763},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12187597155570984},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.1147090494632721}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2502.01059","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01059","pdf_url":"https://arxiv.org/pdf/2502.01059","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2502.01059","doi":"https://doi.org/10.48550/arxiv.2502.01059","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2502.01059","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2502.01059","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2502.01059","pdf_url":"https://arxiv.org/pdf/2502.01059","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407128583.pdf","grobid_xml":"https://content.openalex.org/works/W4407128583.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2896457183","https://openalex.org/W4320005767","https://openalex.org/W4389519982"],"related_works":["https://openalex.org/W4410558890","https://openalex.org/W7150737139","https://openalex.org/W7139925973","https://openalex.org/W7169536934","https://openalex.org/W4390601357","https://openalex.org/W7151896535","https://openalex.org/W4399025557","https://openalex.org/W4410347590","https://openalex.org/W7203533409","https://openalex.org/W4415969974"],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2,101,112,139,170],"biological":[3,44],"data":[4,45,195],"analysis":[5,196],"tools":[6],"and":[7,33,46,52,78,83,99,132,155,168,173,184,197],"large":[8],"language":[9],"models":[10,48],"(LLMs)":[11],"has":[12],"opened":[13],"up":[14],"new":[15],"possibilities":[16],"for":[17,181,192],"utilizing":[18],"AI":[19],"in":[20,49,90,125],"plant":[21,186],"science":[22,187],"research,":[23],"with":[24,73,121,152,166],"the":[25,91,97,102,157,171,190],"potential":[26],"to":[27,30,41,55,95,104,118,137,148,162],"contribute":[28],"significantly":[29],"knowledge":[31,144],"integration":[32],"research":[34,51,66,141,183],"gap":[35],"identification.":[36],"Nonetheless,":[37],"current":[38],"LLMs":[39],"struggle":[40],"handle":[42],"complex":[43],"theoretical":[47],"photosynthesis":[50,65,140,182],"often":[53],"fail":[54],"provide":[56],"accurate":[57],"scientific":[58,119,130],"contexts.":[59],"Therefore,":[60],"this":[61],"study":[62],"proposed":[63],"a":[64,122],"assistant":[67],"(PRAG)":[68],"based":[69],"on":[70],"OpenAI's":[71],"GPT-4o":[72],"retrieval-augmented":[74],"generation":[75],"(RAG)":[76],"techniques":[77],"prompt":[79,92],"optimization.":[80],"Vector":[81],"databases":[82],"an":[84,109],"automated":[85],"feedback":[86],"loop":[87],"were":[88,135],"used":[89,147],"optimization":[93],"process":[94],"enhance":[96],"accuracy":[98],"relevance":[100],"responses":[103,151],"photosynthesis-related":[105],"queries.":[106],"PRAG":[107,161,177],"showed":[108],"average":[110],"improvement":[111],"8.7%":[113],"across":[114],"five":[115],"metrics":[116],"related":[117],"writing,":[120],"25.4%":[123],"increase":[124],"source":[126],"transparency.":[127],"Additionally,":[128],"its":[129],"depth":[131],"domain":[133],"coverage":[134],"comparable":[136],"those":[138],"papers.":[142],"A":[143],"graph":[145],"was":[146],"structure":[149],"PRAG's":[150],"papers":[153],"within":[154],"outside":[156],"database,":[158],"which":[159],"allowed":[160],"match":[163],"key":[164],"entities":[165],"63%":[167],"39.5%":[169],"database":[172],"test":[174],"papers,":[175],"respectively.":[176],"can":[178],"be":[179],"applied":[180],"broader":[185],"domains,":[188],"paving":[189],"way":[191],"more":[193],"in-depth":[194],"predictive":[198],"capabilities.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-02-05T00:00:00"}
