{"id":"https://openalex.org/W4385848263","doi":"https://doi.org/10.48550/arxiv.2308.06111","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":"2023-08-11","ids":{"openalex":"https://openalex.org/W4385848263","doi":"https://doi.org/10.48550/arxiv.2308.06111"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2308.06111","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.06111","pdf_url":"https://arxiv.org/pdf/2308.06111","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/2308.06111","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","observed_orcids":["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":false,"raw_author_name":"Hillebrand, Lars","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin , Germany"],"raw_orcid":null,"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","observed_orcids":["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":"Berger, Armin","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin , Germany"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0000-0003-4685-0847"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deu\u00dfer, Tobias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044214991","display_name":"Tim Dilmaghani","orcid":"https://orcid.org/0009-0003-9134-7746","observed_orcids":["https://orcid.org/0009-0003-9134-7746"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dilmaghani, Tim","raw_affiliation_strings":["PricewaterhouseCoopers GmbH D\u00fcsseldorf , Germany"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0009-0008-6765-1373"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khaled, Mohamed","raw_affiliation_strings":["PricewaterhouseCoopers GmbH D\u00fcsseldorf , Germany"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0009-0000-8222-6078"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kliem, Bernd","raw_affiliation_strings":["PricewaterhouseCoopers GmbH D\u00fcsseldorf , Germany"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0009-0002-6947-9956"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Loitz, R\u00fcdiger","raw_affiliation_strings":["PricewaterhouseCoopers GmbH D\u00fcsseldorf , Germany"],"raw_orcid":null,"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","observed_orcids":["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":"Pielka, Maren","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin , Germany"],"raw_orcid":null,"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","observed_orcids":["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":"Leonhard, David","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin , Germany"],"raw_orcid":null,"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","observed_orcids":["https://orcid.org/0000-0001-6615-2128"]},"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":"Bauckhage, Christian","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS Sankt Augustin , Germany","institution_ids":["https://openalex.org/I4210144576"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064201630","display_name":"Rafet Sifa","orcid":"https://orcid.org/0009-0004-6680-8210","observed_orcids":["https://orcid.org/0009-0004-6680-8210"]},"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":"Sifa, Rafet","raw_affiliation_strings":["Fraunhofer IAIS Sankt Augustin , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IAIS Sankt Augustin , Germany","institution_ids":["https://openalex.org/I4210144576"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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/T10028","display_name":"Topic Modeling","score":0.9545999765396118,"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":0.9545999765396118,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.014800000004470348,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.011300000362098217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/financial-auditing","display_name":"financial auditing","score":0.9520000219345093},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9110000133514404},{"id":"https://openalex.org/keywords/recommender-systems","display_name":"recommender systems","score":0.7059999704360962},{"id":"https://openalex.org/keywords/legal-requirements","display_name":"legal requirements","score":0.5410000085830688},{"id":"https://openalex.org/keywords/accounting-standards","display_name":"accounting standards","score":0.9210000038146973},{"id":"https://openalex.org/keywords/bert","display_name":"BERT","score":0.6449999809265137}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7656763792037964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7571943402290344},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.7440752387046814},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6645530462265015},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6327219605445862},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4911908805370331},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37799352407455444},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3698492646217346},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3546207547187805},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3471810519695282},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.32400768995285034},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1019376814365387},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09423661231994629},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0791749656200409},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2308.06111","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.06111","pdf_url":"https://arxiv.org/pdf/2308.06111","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.2308.06111","doi":"https://doi.org/10.48550/arxiv.2308.06111","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.06111","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:2308.06111","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.06111","pdf_url":"https://arxiv.org/pdf/2308.06111","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":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385848263.pdf","grobid_xml":"https://content.openalex.org/works/W4385848263.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W3139080614","https://openalex.org/W4327810158","https://openalex.org/W4361866125","https://openalex.org/W7133209886"],"related_works":["https://openalex.org/W4360765003","https://openalex.org/W4406457828","https://openalex.org/W2973794125","https://openalex.org/W4391093139","https://openalex.org/W4417118004","https://openalex.org/W4389115191","https://openalex.org/W7140095476","https://openalex.org/W4411843123","https://openalex.org/W4391094171","https://openalex.org/W4412789947"],"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":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2023-08-16T00:00:00"}
