{"id":"https://openalex.org/W4385595254","doi":"https://doi.org/10.1145/3573128.3609344","title":"Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models","display_name":"Improving Zero-Shot Text Matching for Financial Auditing with Large Language Models","publication_year":2023,"publication_date":"2023-08-04","ids":{"openalex":"https://openalex.org/W4385595254","doi":"https://doi.org/10.1145/3573128.3609344"},"language":"en","primary_location":{"id":"doi:10.1145/3573128.3609344","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3573128.3609344","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3573128.3609344","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3573128.3609344","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081939611","display_name":"Lars Hillebrand","orcid":"https://orcid.org/0000-0002-5496-4177"},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Lars Hillebrand","raw_affiliation_strings":["Fraunhofer IAIS, Sankt Augustin, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102998018","display_name":"Armin Berger","orcid":"https://orcid.org/0009-0003-1924-8401"},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Armin Berger","raw_affiliation_strings":["Fraunhofer IAIS, Sankt Augustin, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS, Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003368121","display_name":"Tobias Deu\u00dfer","orcid":"https://orcid.org/0000-0003-4685-0847"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Deu\u00dfer","raw_affiliation_strings":["Fraunhofer IAIS, Sankt Augustin, Germany and University of Bonn in Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS, Sankt Augustin, Germany and University of Bonn in Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044214991","display_name":"Tim Dilmaghani","orcid":"https://orcid.org/0009-0003-9134-7746"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tim Dilmaghani","raw_affiliation_strings":["PricewaterhouseCoopers GmbH, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"PricewaterhouseCoopers GmbH, D\u00fcsseldorf, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084289640","display_name":"M. Ben Khaled","orcid":"https://orcid.org/0009-0008-6765-1373"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohamed Khaled","raw_affiliation_strings":["PricewaterhouseCoopers GmbH, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"PricewaterhouseCoopers GmbH, D\u00fcsseldorf, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037349423","display_name":"Bernd Kliem","orcid":"https://orcid.org/0009-0000-8222-6078"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bernd Kliem","raw_affiliation_strings":["PricewaterhouseCoopers GmbH, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"PricewaterhouseCoopers GmbH, D\u00fcsseldorf, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026553005","display_name":"R\u00fcdiger Loitz","orcid":"https://orcid.org/0009-0002-6947-9956"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R\u00fcdiger Loitz","raw_affiliation_strings":["PricewaterhouseCoopers GmbH, D\u00fcsseldorf, Germany"],"affiliations":[{"raw_affiliation_string":"PricewaterhouseCoopers GmbH, D\u00fcsseldorf, Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054556600","display_name":"Maren Pielka","orcid":"https://orcid.org/0000-0001-9610-6026"},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Maren Pielka","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091957484","display_name":"David Leonhard","orcid":"https://orcid.org/0009-0002-4434-1889"},"institutions":[{"id":"https://openalex.org/I4210144576","display_name":"Fraunhofer Institute for Intelligent Analysis and Information Systems","ror":"https://ror.org/04nc32781","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210144576","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"David Leonhard","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin, Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS Sankt Augustin, Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003875445","display_name":"Christian Bauckhage","orcid":"https://orcid.org/0000-0001-6615-2128"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Bauckhage","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin, Germany and University of Bonn in Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS Sankt Augustin, Germany and University of Bonn in Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064201630","display_name":"Rafet Sifa","orcid":"https://orcid.org/0009-0004-6680-8210"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rafet Sifa","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin, Germany and University of Bonn in Germany"],"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS Sankt Augustin, Germany and University of Bonn in Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5081939611"],"corresponding_institution_ids":["https://openalex.org/I4210144576"],"apc_list":null,"apc_paid":null,"fwci":6.239,"has_fulltext":true,"cited_by_count":25,"citation_normalized_percentile":{"value":0.96605315,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9972000122070312,"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"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.9972000122070312,"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/T10028","display_name":"Topic Modeling","score":0.9965000152587891,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9922000169754028,"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":0.791332483291626},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7565748691558838},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.7063848972320557},{"id":"https://openalex.org/keywords/audit","display_name":"Audit","score":0.6935833692550659},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6203777194023132},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4832097291946411},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43168431520462036},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4314045310020447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42180508375167847},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3707636594772339},{"id":"https://openalex.org/keywords/accounting","display_name":"Accounting","score":0.28182506561279297},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11024719476699829},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0881401002407074}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791332483291626},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7565748691558838},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.7063848972320557},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6935833692550659},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6203777194023132},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4832097291946411},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43168431520462036},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4314045310020447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42180508375167847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3707636594772339},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.28182506561279297},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11024719476699829},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0881401002407074},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3573128.3609344","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3573128.3609344","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3573128.3609344","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/459475","is_oa":true,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/459475","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":{"id":"doi:10.1145/3573128.3609344","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3573128.3609344","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3573128.3609344","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Symposium on Document Engineering 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6955755495","display_name":null,"funder_award_id":"Germany","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385595254.pdf","grobid_xml":"https://content.openalex.org/works/W4385595254.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2970641574","https://openalex.org/W2973794125","https://openalex.org/W3195248505","https://openalex.org/W4221143046","https://openalex.org/W4313007903","https://openalex.org/W4317829538","https://openalex.org/W4318147798","https://openalex.org/W4360765003"],"related_works":["https://openalex.org/W3196747313","https://openalex.org/W3097571385","https://openalex.org/W2359001871","https://openalex.org/W3033862527","https://openalex.org/W4287761227","https://openalex.org/W3033942572","https://openalex.org/W3008110149","https://openalex.org/W4381786178","https://openalex.org/W4316012698","https://openalex.org/W3177920269"],"abstract_inverted_index":{"Auditing":[0],"financial":[1],"documents":[2],"is":[3,53],"a":[4,28,63,69,78,87,93,104],"very":[5],"tedious":[6],"and":[7,46,108],"time-consuming":[8],"process.":[9],"As":[10],"of":[11,34,90,95],"today,":[12],"it":[13],"can":[14],"already":[15],"be":[16,43],"simplified":[17],"by":[18],"employing":[19],"AI-based":[20],"solutions":[21],"to":[22,42],"recommend":[23],"relevant":[24],"text":[25],"passages":[26],"from":[27],"report":[29],"for":[30],"each":[31],"legal":[32,101],"requirement":[33,102],"rigorous":[35],"accounting":[36],"standards.":[37],"However,":[38],"these":[39,111],"methods":[40],"need":[41],"fine-tuned":[44],"regularly,":[45],"they":[47],"require":[48],"abundant":[49],"annotated":[50],"data,":[51],"which":[52],"often":[54],"lacking":[55],"in":[56,75],"industrial":[57],"environments.":[58],"Hence,":[59],"we":[60],"present":[61],"ZeroShotALI,":[62],"novel":[64],"recommender":[65],"system":[66],"that":[67,86],"leverages":[68],"state-of-the-art":[70],"large":[71],"language":[72],"model":[73,107],"(LLM)":[74],"conjunction":[76],"with":[77,103],"domain-specifically":[79],"optimized":[80],"transformer-based":[81],"text-matching":[82],"solution.":[83],"We":[84],"find":[85],"two-step":[88],"approach":[89],"first":[91],"retrieving":[92],"number":[94],"best":[96],"matching":[97],"document":[98],"sections":[99],"per":[100],"custom":[105],"BERT-based":[106],"second":[109],"filtering":[110],"selections":[112],"using":[113],"an":[114],"LLM":[115],"yields":[116],"significant":[117],"performance":[118],"improvements":[119],"over":[120],"existing":[121],"approaches.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
