{"id":"https://openalex.org/W4404166038","doi":"https://doi.org/10.1109/fllm63129.2024.10852504","title":"LLM-centric pipeline for information extraction from invoices","display_name":"LLM-centric pipeline for information extraction from invoices","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4404166038","doi":"https://doi.org/10.1109/fllm63129.2024.10852504"},"language":"en","primary_location":{"id":"doi:10.1109/fllm63129.2024.10852504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04772570/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075183190","display_name":"Faiza Loukil","orcid":"https://orcid.org/0000-0003-4753-060X"},"institutions":[{"id":"https://openalex.org/I70900168","display_name":"Universit\u00e9 Savoie Mont Blanc","ror":"https://ror.org/04gqg1a07","country_code":"FR","type":"education","lineage":["https://openalex.org/I70900168"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Faiza Loukil","raw_affiliation_strings":["LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","institution_ids":["https://openalex.org/I70900168"]},{"raw_affiliation_string":"LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114564211","display_name":"Sarah Cadereau","orcid":null},"institutions":[{"id":"https://openalex.org/I70900168","display_name":"Universit\u00e9 Savoie Mont Blanc","ror":"https://ror.org/04gqg1a07","country_code":"FR","type":"education","lineage":["https://openalex.org/I70900168"]},{"id":"https://openalex.org/I4210098847","display_name":"Cegedim (France)","ror":"https://ror.org/012bs5594","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210098847"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sarah Cadereau","raw_affiliation_strings":["LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","Cegedim (France)","LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","institution_ids":["https://openalex.org/I70900168"]},{"raw_affiliation_string":"Cegedim (France)","institution_ids":["https://openalex.org/I4210098847"]},{"raw_affiliation_string":"LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031030703","display_name":"Herv\u00e9 Verjus","orcid":"https://orcid.org/0000-0003-3258-1826"},"institutions":[{"id":"https://openalex.org/I70900168","display_name":"Universit\u00e9 Savoie Mont Blanc","ror":"https://ror.org/04gqg1a07","country_code":"FR","type":"education","lineage":["https://openalex.org/I70900168"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Herv\u00e9 Verjus","raw_affiliation_strings":["LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","institution_ids":["https://openalex.org/I70900168"]},{"raw_affiliation_string":"LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114564212","display_name":"Matt\u00e9o Galfr\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098847","display_name":"Cegedim (France)","ror":"https://ror.org/012bs5594","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210098847"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Matt\u00e9o Galfre","raw_affiliation_strings":["Cegedim,Lyon,France","Cegedim (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cegedim,Lyon,France","institution_ids":["https://openalex.org/I4210098847"]},{"raw_affiliation_string":"Cegedim (France)","institution_ids":["https://openalex.org/I4210098847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010294597","display_name":"Kav\u00e9 Salamatian","orcid":"https://orcid.org/0000-0001-5557-9134"},"institutions":[{"id":"https://openalex.org/I70900168","display_name":"Universit\u00e9 Savoie Mont Blanc","ror":"https://ror.org/04gqg1a07","country_code":"FR","type":"education","lineage":["https://openalex.org/I70900168"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Kav\u00e9 Salamatian","raw_affiliation_strings":["LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","DATASPHERE - Dynamique du pouvoir dans l'anthropocene (46 All\u00e9e d'Italie, \r\n69007 Lyon - France)","LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","institution_ids":["https://openalex.org/I70900168"]},{"raw_affiliation_string":"DATASPHERE - Dynamique du pouvoir dans l'anthropocene (46 All\u00e9e d'Italie, \r\n69007 Lyon - France)","institution_ids":[]},{"raw_affiliation_string":"LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083083774","display_name":"David T\u00e9lisson","orcid":null},"institutions":[{"id":"https://openalex.org/I70900168","display_name":"Universit\u00e9 Savoie Mont Blanc","ror":"https://ror.org/04gqg1a07","country_code":"FR","type":"education","lineage":["https://openalex.org/I70900168"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"David Telisson","raw_affiliation_strings":["LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LISTIC, University Savoie Mont Blanc,Annecy-le-Vieux,France","institution_ids":["https://openalex.org/I70900168"]},{"raw_affiliation_string":"LISTIC - Laboratoire d'Informatique, Syst\u00e8mes, Traitement de l'Information et de la Connaissance (BP 80439 74944 ANNECY LE VIEUX Cedex - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114564213","display_name":"Quentin Kembellec","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098847","display_name":"Cegedim (France)","ror":"https://ror.org/012bs5594","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210098847"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Quentin Kembellec","raw_affiliation_strings":["Cegedim,Lyon,France","Cegedim (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cegedim,Lyon,France","institution_ids":["https://openalex.org/I4210098847"]},{"raw_affiliation_string":"Cegedim (France)","institution_ids":["https://openalex.org/I4210098847"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5092531945","display_name":"Olivier Le Van","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098847","display_name":"Cegedim (France)","ror":"https://ror.org/012bs5594","country_code":"FR","type":"company","lineage":["https://openalex.org/I4210098847"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Le Van","raw_affiliation_strings":["Cegedim,Lyon,France","Cegedim (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cegedim,Lyon,France","institution_ids":["https://openalex.org/I4210098847"]},{"raw_affiliation_string":"Cegedim (France)","institution_ids":["https://openalex.org/I4210098847"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5075183190"],"corresponding_institution_ids":["https://openalex.org/I70900168"],"apc_list":null,"apc_paid":null,"fwci":1.296,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.84141656,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"569","last_page":"575"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.4636000096797943,"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/T13734","display_name":"Advanced Computational Techniques and Applications","score":0.4636000096797943,"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/T14339","display_name":"Image Processing and 3D Reconstruction","score":0.4106000065803528,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/pipeline","display_name":"Pipeline (software)","score":0.755263090133667},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6354941725730896},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5555324554443359},{"id":"https://openalex.org/keywords/extraction","display_name":"Extraction (chemistry)","score":0.5535703301429749},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2692389190196991},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10005947947502136},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08630332350730896},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06397035717964172}],"concepts":[{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.755263090133667},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6354941725730896},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5555324554443359},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.5535703301429749},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2692389190196991},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10005947947502136},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08630332350730896},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06397035717964172}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/fllm63129.2024.10852504","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852504","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04772570v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04772570","pdf_url":"https://hal.science/hal-04772570/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Foundation and Large Language Models (FLLM2024), Nov 2024, Dubai, United Arab Emirates","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04772570v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04772570","pdf_url":"https://hal.science/hal-04772570/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Foundation and Large Language Models (FLLM2024), Nov 2024, Dubai, United Arab Emirates","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404166038.pdf","grobid_xml":"https://content.openalex.org/works/W4404166038.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Extracting":[0],"information":[1,143,184,217],"from":[2,40,88,144,185],"digital":[3],"documents":[4,58,92,180],"is":[5,104,147],"an":[6,95],"evolving":[7],"area":[8],"of":[9,45,66,77,91,118,126,136,173,216],"research,":[10],"especially":[11],"with":[12,54,159,200],"the":[13,43,61,124,134,137,171,201,212],"recent":[14],"advances":[15],"in":[16,31],"artificial":[17],"intelligence":[18],"and":[19,64,85,100,109,129,198,207,214,227],"computer":[20],"vision.":[21],"Recently,":[22],"Large":[23],"Language":[24],"Models":[25],"(LLMs)":[26],"have":[27],"shown":[28],"remarkable":[29],"performance":[30],"various":[32],"natural":[33],"language":[34],"processing":[35],"tasks,":[36],"including":[37,196],"data":[38,87],"extraction":[39,117,218],"documents.":[41],"However,":[42,102],"accuracy":[44,213],"these":[46],"models":[47],"can":[48],"be":[49,157],"significantly":[50,210],"affected":[51],"when":[52],"dealing":[53],"large":[55],"or":[56],"complicated":[57],"due":[59],"to":[60,107,132,140,156,169,179,181],"inherent":[62],"complexity":[63],"variability":[65],"rich":[67],"formats.":[68],"In":[69,162],"this":[70,163],"paper,":[71,164],"we":[72,165,209],"target":[73],"a":[74,127,151],"specific":[75],"type":[76],"complex":[78],"document:":[79],"financial":[80,186],"invoices.OCR":[81],"technology":[82],"extracts":[83],"editable":[84],"searchable":[86],"different":[89],"types":[90],"transformed":[93],"into":[94,115],"image,":[96],"e.g.,":[97],"scanned":[98],"documents,":[99],"PDFs.":[101],"OCR":[103,121,146,194],"highly":[105],"sensitive":[106],"noise":[108],"image":[110],"mis-alignment":[111],"that":[112,154,191],"frequently":[113],"results":[114],"wrong":[116],"texts.":[119],"Moreover,":[120],"cannot":[122],"understand":[123,133],"structure":[125],"document,":[128],"leverage":[130],"it":[131],"semantic":[135],"document\u2019s":[138],"content":[139],"extract":[141,182],"structured":[142,183],"document.":[145],"therefore":[148],"considered":[149],"as":[150],"preprocessing":[152],"step":[153],"need":[155],"completed":[158],"further":[160],"processing.":[161],"use":[166],"text-based":[167],"LLMs":[168],"enrich":[170],"outputs":[172],"Optical":[174],"Character":[175],"Recognition":[176],"(OCR)":[177],"applied":[178],"invoices.":[187],"We":[188],"show":[189],"here,":[190],"by":[192],"fusing":[193],"engines,":[195],"Tesseract":[197],"DocTR,":[199],"two":[202,221],"open-source":[203],"LLM":[204],"models,":[205],"Llama3":[206],"Mistral,":[208],"improve":[211],"reliability":[215],"operations":[219],"on":[220],"datasets":[222],"featuring":[223],"business":[224],"documents:":[225],"SROIE":[226],"FATURA":[228],"datasets.":[229]},"counts_by_year":[{"year":2025,"cited_by_count":4}],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}