{"id":"https://openalex.org/W4403230932","doi":"https://doi.org/10.1021/acs.jcim.4c00882","title":"How Does a Generative Large Language Model Perform on Domain-Specific Information Extraction?\u2500A Comparison between GPT-4 and a Rule-Based Method on Band Gap Extraction","display_name":"How Does a Generative Large Language Model Perform on Domain-Specific Information Extraction?\u2500A Comparison between GPT-4 and a Rule-Based Method on Band Gap Extraction","publication_year":2024,"publication_date":"2024-10-08","ids":{"openalex":"https://openalex.org/W4403230932","doi":"https://doi.org/10.1021/acs.jcim.4c00882","pmid":"https://pubmed.ncbi.nlm.nih.gov/39375999"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c00882","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00882","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092231017","display_name":"Xin Wang","orcid":"https://orcid.org/0009-0003-5454-859X"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["School of Library and Information Studies, The University of Oklahoma, 401 West Brooks, Norman, Oklahoma 73019, United States"],"raw_orcid":"https://orcid.org/0009-0003-5454-859X","affiliations":[{"raw_affiliation_string":"School of Library and Information Studies, The University of Oklahoma, 401 West Brooks, Norman, Oklahoma 73019, United States","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053218750","display_name":"Liangliang Huang","orcid":"https://orcid.org/0000-0003-2358-9375"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangliang Huang","raw_affiliation_strings":["School of Sustainable Chemical, Biological and Materials Engineering, The University of Oklahoma, 100 E. Boyd St., Norman, Oklahoma 73019, United States"],"raw_orcid":"https://orcid.org/0000-0003-2358-9375","affiliations":[{"raw_affiliation_string":"School of Sustainable Chemical, Biological and Materials Engineering, The University of Oklahoma, 100 E. Boyd St., Norman, Oklahoma 73019, United States","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052569938","display_name":"Shuozhi Xu","orcid":"https://orcid.org/0000-0003-0121-9445"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuozhi Xu","raw_affiliation_strings":["School of Aerospace and Mechanical Engineering, The University of Oklahoma, 865 Asp Ave., Norman, Oklahoma 73019, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Aerospace and Mechanical Engineering, The University of Oklahoma, 865 Asp Ave., Norman, Oklahoma 73019, United States","institution_ids":["https://openalex.org/I8692664"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008357796","display_name":"Kun L\u00fc","orcid":"https://orcid.org/0000-0001-5614-7042"},"institutions":[{"id":"https://openalex.org/I8692664","display_name":"University of Oklahoma","ror":"https://ror.org/02aqsxs83","country_code":"US","type":"education","lineage":["https://openalex.org/I8692664"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kun Lu","raw_affiliation_strings":["School of Library and Information Studies, The University of Oklahoma, 401 West Brooks, Norman, Oklahoma 73019, United States"],"raw_orcid":"https://orcid.org/0000-0001-5614-7042","affiliations":[{"raw_affiliation_string":"School of Library and Information Studies, The University of Oklahoma, 401 West Brooks, Norman, Oklahoma 73019, United States","institution_ids":["https://openalex.org/I8692664"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5008357796"],"corresponding_institution_ids":["https://openalex.org/I8692664"],"apc_list":null,"apc_paid":null,"fwci":2.9212,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.91893436,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"64","issue":"20","first_page":"7895","last_page":"7904"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998000264167786,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9758999943733215,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.7530217170715332},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6109932661056519},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5589531660079956},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5459110736846924},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5295442342758179},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5285723805427551},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49172714352607727},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4228641986846924},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.2819364666938782},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20670992136001587},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.18896213173866272}],"concepts":[{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.7530217170715332},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6109932661056519},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5589531660079956},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5459110736846924},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5295442342758179},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5285723805427551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49172714352607727},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4228641986846924},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.2819364666938782},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20670992136001587},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.18896213173866272},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.4c00882","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00882","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:39375999","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39375999","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F8625567347","display_name":"Office of the Vice President for Research and Partnerships","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2121244856","https://openalex.org/W2149369282","https://openalex.org/W2159335058","https://openalex.org/W2163107094","https://openalex.org/W2166468803","https://openalex.org/W2169491861","https://openalex.org/W2313881975","https://openalex.org/W2523785361","https://openalex.org/W2767891136","https://openalex.org/W2808304511","https://openalex.org/W2911489562","https://openalex.org/W2953641512","https://openalex.org/W2964864162","https://openalex.org/W3047398431","https://openalex.org/W3127365350","https://openalex.org/W3201869313","https://openalex.org/W4205340501","https://openalex.org/W4206078246","https://openalex.org/W4225409008","https://openalex.org/W4293175993","https://openalex.org/W4309674289","https://openalex.org/W4362640271","https://openalex.org/W4385671288","https://openalex.org/W4386827094","https://openalex.org/W4387773384","https://openalex.org/W4390064615","https://openalex.org/W4390195781","https://openalex.org/W4390824394","https://openalex.org/W4391836235","https://openalex.org/W4391862446","https://openalex.org/W4392002118","https://openalex.org/W4397004462","https://openalex.org/W4398777692","https://openalex.org/W4401023556","https://openalex.org/W4401722919","https://openalex.org/W4403447187"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"The":[0,157],"advent":[1],"of":[2,13,35,78,90,95,113,140,148,203],"generative":[3,22,231],"Large":[4],"Language":[5,15],"Models":[6],"(LLMs)":[7],"has":[8,54,174],"greatly":[9],"impacted":[10],"the":[11,33,58,82,106,122,141,144,149,154,191,201,209,213,219],"field":[12],"Natural":[14],"Processing.":[16],"However,":[17],"it":[18,172],"is":[19,65,71,75,94,208],"inconclusive":[20],"how":[21],"LLMs":[23,232],"perform":[24],"on":[25,44,46,99,190],"domain-specific":[26,234],"information":[27,40,49,92,120,235],"extraction":[28,41,222,236],"tasks.":[29,237],"This":[30,224],"study":[31,207,225],"compares":[32],"performance":[34,162],"GPT-4":[36,107,150,158,214],"and":[37,146,166,182,216],"a":[38,51,76,88,110],"rule-based":[39,123,155],"method":[42,124],"based":[43,189],"ChemDataExtractor":[45,217],"band":[47,118,179,184,220],"gap":[48,119,180,185,221],"extraction,":[50],"task":[52],"that":[53,93,105],"important":[55],"implications":[56],"for":[57,67,198,218,233],"materials":[59,83],"science":[60,84],"domain.":[61],"No":[62],"training":[63,79],"data":[64,80],"required":[66],"either":[68],"method,":[69],"which":[70],"desirable":[72],"because":[73],"there":[74],"lack":[77],"in":[81,115,163,176],"domain":[85],"compared":[86,152],"with":[87],"variety":[89],"material":[91,168],"interest.":[96],"Manual":[97],"evaluation":[98],"415":[100],"randomly":[101],"selected":[102],"articles":[103],"showed":[104],"model":[108,151,159,215],"achieved":[109],"higher":[111],"level":[112],"accuracy":[114,197],"extracting":[116],"materials'":[117],"than":[121],"(Correctness":[125],"87.95%":[126],"vs":[127,132,136],"51.08%,":[128],"Partial":[129],"correctness":[130],"11.33%":[131],"36.87%,":[133],"incorrectness":[134],"0.72%":[135],"12.05%).":[137],"Further":[138],"analysis":[139,193],"errors":[142],"reveals":[143],"strengths":[145],"weaknesses":[147,175],"to":[153,195,211,228],"method.":[156],"shows":[160],"stronger":[161],"interdependency":[164],"resolution":[165],"complicated":[167],"name":[169],"recognition,":[170],"while":[171],"also":[173],"hallucination,":[177],"identifying":[178,183],"values,":[181],"types.":[186],"Revised":[187],"prompt":[188],"error":[192],"leads":[194],"improved":[196],"GPT-4.":[199],"To":[200],"best":[202],"our":[204],"knowledge,":[205],"this":[206],"first":[210],"compare":[212],"task.":[223],"provides":[226],"evidence":[227],"support":[229],"using":[230]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}