{"id":"https://openalex.org/W4409987565","doi":"https://doi.org/10.1021/acs.jcim.5c00248","title":"Rapid Adaptation of Chemical Named Entity Recognition Using Few-Shot Learning and LLM Distillation","display_name":"Rapid Adaptation of Chemical Named Entity Recognition Using Few-Shot Learning and LLM Distillation","publication_year":2025,"publication_date":"2025-05-01","ids":{"openalex":"https://openalex.org/W4409987565","doi":"https://doi.org/10.1021/acs.jcim.5c00248","pmid":"https://pubmed.ncbi.nlm.nih.gov/40310732"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.5c00248","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00248","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":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/2565842","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100333795","display_name":"Yue Zhang","orcid":"https://orcid.org/0000-0003-2844-6875"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yue Zhang","raw_affiliation_strings":["Center for Plastics Innovation","Department of Electrical and Computer Engineering","University of Delaware"],"affiliations":[{"raw_affiliation_string":"Center for Plastics Innovation","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering","institution_ids":[]},{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066110304","display_name":"Dionisios G. Vlachos","orcid":"https://orcid.org/0000-0002-6795-8403"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dionisios G. Vlachos","raw_affiliation_strings":["Center for Plastics Innovation","Department of Chemical and Biomolecular Engineering","University of Delaware"],"affiliations":[{"raw_affiliation_string":"Center for Plastics Innovation","institution_ids":[]},{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering","institution_ids":[]},{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088103067","display_name":"Dongxia Liu","orcid":"https://orcid.org/0000-0001-8712-2219"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dongxia Liu","raw_affiliation_strings":["Center for Plastics Innovation","Department of Chemical and Biomolecular Engineering","University of Delaware"],"affiliations":[{"raw_affiliation_string":"Center for Plastics Innovation","institution_ids":[]},{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering","institution_ids":[]},{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101716412","display_name":"Hui Fang","orcid":"https://orcid.org/0009-0003-1904-787X"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hui Fang","raw_affiliation_strings":["Center for Plastics Innovation","Department of Electrical and Computer Engineering","University of Delaware"],"affiliations":[{"raw_affiliation_string":"Center for Plastics Innovation","institution_ids":[]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering","institution_ids":[]},{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066110304","https://openalex.org/A5088103067","https://openalex.org/A5100333795","https://openalex.org/A5101716412"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":22.2151,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.99259222,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"65","issue":"9","first_page":"4334","last_page":"4345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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":0.9997000098228455,"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/T11719","display_name":"Data Quality and Management","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9900000095367432,"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/distillation","display_name":"Distillation","score":0.599571704864502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5894500613212585},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5278753638267517},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5005226135253906},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.48606494069099426},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4632054567337036},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39403244853019714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3531262278556824},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.20690375566482544},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.1857742965221405},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08758065104484558},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.06931227445602417},{"id":"https://openalex.org/keywords/organic-chemistry","display_name":"Organic chemistry","score":0.06756836175918579}],"concepts":[{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.599571704864502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5894500613212585},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5278753638267517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5005226135253906},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.48606494069099426},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4632054567337036},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39403244853019714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3531262278556824},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.20690375566482544},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.1857742965221405},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08758065104484558},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.06931227445602417},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.06756836175918579}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.5c00248","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.5c00248","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:40310732","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40310732","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},{"id":"pmh:oai:osti.gov:2565842","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2565842","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:2565842","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2565842","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2"}],"awards":[{"id":"https://openalex.org/G1880822571","display_name":null,"funder_award_id":"DE-SC0021166","funder_id":"https://openalex.org/F4320337480","funder_display_name":"Basic Energy Sciences"}],"funders":[{"id":"https://openalex.org/F4320337480","display_name":"Basic Energy Sciences","ror":"https://ror.org/05mg91w61"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1847618513","https://openalex.org/W2755202310","https://openalex.org/W2766362701","https://openalex.org/W2911489562","https://openalex.org/W2936166854","https://openalex.org/W2964864162","https://openalex.org/W2969656782","https://openalex.org/W2970771982","https://openalex.org/W2980932864","https://openalex.org/W2990138404","https://openalex.org/W3015453090","https://openalex.org/W3115677442","https://openalex.org/W3127365350","https://openalex.org/W3146601652","https://openalex.org/W3176489198","https://openalex.org/W3177312484","https://openalex.org/W3186908817","https://openalex.org/W3210396023","https://openalex.org/W3213082281","https://openalex.org/W3213675203","https://openalex.org/W4214535912","https://openalex.org/W4248414713","https://openalex.org/W4281476575","https://openalex.org/W4281559792","https://openalex.org/W4282935671","https://openalex.org/W4283729620","https://openalex.org/W4319163914","https://openalex.org/W4380434564","https://openalex.org/W4391836235","https://openalex.org/W4399442007","https://openalex.org/W4404719819","https://openalex.org/W4405590246"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2980279061","https://openalex.org/W2334685461","https://openalex.org/W2366718574","https://openalex.org/W2359774528","https://openalex.org/W4298312966","https://openalex.org/W2325697621"],"abstract_inverted_index":{"Named":[0],"entity":[1,117,130,177],"recognition":[2,131],"(NER)":[3],"has":[4],"been":[5],"widely":[6],"used":[7],"in":[8,45,73,132],"chemical":[9,19,23,47,98,122,148,156],"text":[10],"mining":[11],"for":[12,43,210,226,237],"the":[13,46,140,163,184,193,219],"automatic":[14],"identification":[15],"and":[16,61,70,77,179,239],"extraction":[17],"of":[18,64,97,106,142,186,213,222],"entities.":[20],"However,":[21],"existing":[22,155],"NER":[24,87,149,157,166,214],"systems":[25],"primarily":[26],"focus":[27],"on":[28,38,58,145,153],"scenarios":[29],"with":[30,172,199],"abundant":[31,125],"training":[32],"data,":[33,205],"requiring":[34],"significant":[35],"human":[36],"effort":[37],"annotations.":[39],"This":[40,66],"poses":[41],"challenges":[42],"applications":[44],"field,":[48],"such":[49],"as":[50,183],"catalysis,":[51],"where":[52],"many":[53],"advancements":[54],"have":[55],"traditionally":[56],"relied":[57],"trial-and-error":[59],"investigations":[60],"incremental":[62],"adjustment":[63],"variables.":[65],"hinders":[67],"catalysis":[68],"science":[69],"technology":[71],"progress":[72],"addressing":[74],"emerging":[75],"energy":[76],"environmental":[78],"crises.":[79],"In":[80],"this":[81,230],"work,":[82],"we":[83,190],"propose":[84],"a":[85,103,112,146,207,233],"few-shot":[86,147,165],"model":[88,110,144,167,195,202,235],"that":[89,162],"can":[90,168,196],"quickly":[91],"adapt":[92],"to":[93,115,127],"extract":[94],"new":[95,208],"types":[96],"entities":[99],"by":[100],"using":[101],"only":[102,173],"limited":[104],"number":[105,185],"annotated":[107,204],"examples.":[108],"Our":[109,216],"employs":[111],"metric-learning":[113],"approach":[114,217],"transfer":[116],"similarity":[118],"knowledge":[119,220,231],"from":[120],"high-resource":[121],"domains":[123,135],"(with":[124],"annotations)":[126],"enable":[128],"effective":[129],"low-resource":[133],"specialized":[134],"(limited":[136],"annotation).":[137],"We":[138],"validate":[139],"effectiveness":[141],"our":[143],"benchmark":[150],"built":[151],"based":[152],"six":[154],"data":[158],"sets.":[159],"Experiments":[160],"show":[161],"proposed":[164,194],"achieve":[169],"reasonable":[170],"performance":[171],"5":[174],"examples":[175,187],"per":[176],"type":[178],"shows":[180],"consistent":[181],"improvement":[182],"increases.":[188],"Furthermore,":[189],"demonstrate":[191],"how":[192],"be":[197],"trained":[198],"large":[200,223],"language":[201,224],"(LLM)":[203],"opening":[206],"pathway":[209],"rapid":[211],"adaptation":[212],"systems.":[215],"leverages":[218],"broadness":[221],"models":[225],"chemistry":[227],"while":[228],"distilling":[229],"into":[232],"lightweight":[234],"suitable":[236],"efficient":[238],"in-house":[240],"use.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}