{"id":"https://openalex.org/W7127149642","doi":"https://doi.org/10.48550/arxiv.2601.23200","title":"Large Language Models for Patent Classification: Strengths, Trade-offs, and the Long Tail Effect","display_name":"Large Language Models for Patent Classification: Strengths, Trade-offs, and the Long Tail Effect","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7127149642","doi":"https://doi.org/10.48550/arxiv.2601.23200"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2601.23200","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119758605","display_name":"Lorenzo Emer","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Emer, Lorenzo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124866914","display_name":"Marco Lippi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lippi, Marco","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110939272","display_name":"Andrea Mina","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mina, Andrea","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5122113799","display_name":"Andrea Vandin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vandin, Andrea","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5119758605"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"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/T10856","display_name":"Intellectual Property and Patents","score":0.7803000211715698,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10856","display_name":"Intellectual Property and Patents","score":0.7803000211715698,"subfield":{"id":"https://openalex.org/subfields/1405","display_name":"Management of Technology and Innovation"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.045899998396635056,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.023900000378489494,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6736999750137329},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6276999711990356},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5945000052452087},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.41350001096725464},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3790999948978424},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.37059998512268066}],"concepts":[{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6736999750137329},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6276999711990356},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5547000169754028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4864000082015991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48539999127388},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.41350001096725464},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.37059998512268066},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.262800008058548},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2601.23200","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2601.23200","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.23200","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2601.23200","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8563886880874634}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Patent":[0],"classification":[1,221],"into":[2],"CPC":[3,136],"codes":[4],"underpins":[5],"large":[6,39,46],"scale":[7,40],"analyses":[8],"of":[9,75,114,203,232],"technological":[10,65],"change":[11],"but":[12,138],"remains":[13],"challenging":[14],"due":[15],"to":[16,200],"its":[17],"hierarchical,":[18],"multi":[19],"label,":[20],"and":[21,81,83,103,107,175,190,215,218,236],"highly":[22,89],"imbalanced":[23,90],"structure.":[24],"While":[25],"pre":[26],"Generative":[27],"AI":[28],"supervised":[29],"encoder":[30,76,123,173,195,225],"based":[31,77,124,174,177,196],"models":[32,48,125,197],"became":[33],"the":[34,115,228],"de":[35],"facto":[36],"standard":[37],"for":[38,60],"patent":[41,183],"classification,":[42],"recent":[43],"advances":[44],"in":[45,182],"language":[47],"(LLMs)":[49],"raise":[50],"questions":[51],"about":[52],"whether":[53],"they":[54],"can":[55],"provide":[56],"complementary":[57,180],"capabilities,":[58],"particularly":[59,164],"rare":[61,141],"or":[62,160],"weakly":[63,161],"represented":[64],"categories.":[66],"In":[67,143],"this":[68],"work,":[69],"we":[70],"perform":[71],"a":[72,88],"systematic":[73],"comparison":[74],"classifiers":[78],"(BERT,":[79],"SciBERT,":[80],"PatentSBERTa)":[82],"open":[84],"weight":[85],"LLMs":[86,97,145,233],"on":[87,134,140,150],"benchmark":[91],"dataset":[92],"(USPTO":[93],"70k).":[94],"We":[95,185],"evaluate":[96],"under":[98,234],"zero":[99],"shot,":[100,102],"few":[101],"retrieval":[104],"augmented":[105],"prompting,":[106],"further":[108],"assess":[109],"parameter":[110],"efficient":[111,206],"fine":[112],"tuning":[113],"best":[116],"performing":[117],"model.":[118],"Our":[119],"results":[120,133,211],"show":[121],"that":[122,172,194,223],"achieve":[126,146],"higher":[127,148,166],"aggregate":[128],"performance,":[129],"driven":[130],"by":[131],"strong":[132],"frequent":[135],"subclasses,":[137,152],"struggle":[139],"ones.":[142],"contrast,":[144],"relatively":[147],"performance":[149],"infrequent":[151],"often":[153],"associated":[154],"with":[155,227],"early":[156],"stage,":[157],"cross":[158],"domain,":[159],"institutionalised":[162],"technologies,":[163],"at":[165],"hierarchical":[167],"levels.":[168],"These":[169],"findings":[170],"indicate":[171],"LLM":[176],"approaches":[178,222],"play":[179],"roles":[181],"classification.":[184],"additionally":[186],"quantify":[187],"inference":[188],"time":[189],"energy":[191],"consumption,":[192],"showing":[193],"are":[198],"up":[199],"three":[201],"orders":[202],"magnitude":[204],"more":[205],"than":[207],"LLMs.":[208],"Overall,":[209],"our":[210],"inform":[212],"responsible":[213],"patentometrics":[214],"technology":[216],"mapping,":[217],"motivate":[219],"hybrid":[220],"combine":[224],"efficiency":[226],"long":[229],"tail":[230],"coverage":[231],"computational":[235],"environmental":[237],"constraints.":[238]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-03T00:00:00"}