{"id":"https://openalex.org/W7134809188","doi":"https://doi.org/10.1007/s10032-026-00572-y","title":"Beyond Accuracy: Understanding Model Confidence in Key Information Extraction with Conformal Prediction","display_name":"Beyond Accuracy: Understanding Model Confidence in Key Information Extraction with Conformal Prediction","publication_year":2026,"publication_date":"2026-03-10","ids":{"openalex":"https://openalex.org/W7134809188","doi":"https://doi.org/10.1007/s10032-026-00572-y"},"language":"en","primary_location":{"id":"doi:10.1007/s10032-026-00572-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-026-00572-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-026-00572-y.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10032-026-00572-y.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075345053","display_name":"Alexander Rombach","orcid":"https://orcid.org/0000-0002-9173-4215"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alexander Rombach","raw_affiliation_strings":["German Research Center for Artificial Intelligence, Campus D3 2, Saarbr\u00fccken, Germany","Saarland University, Campus D3 2, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Campus D3 2, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Saarland University, Campus D3 2, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045367105","display_name":"Nijat Mehdiyev","orcid":"https://orcid.org/0000-0001-7899-1017"},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]},{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Nijat Mehdiyev","raw_affiliation_strings":["German Research Center for Artificial Intelligence, Campus D3 2, Saarbr\u00fccken, Germany","Saarland University, Campus D3 2, Saarbr\u00fccken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"German Research Center for Artificial Intelligence, Campus D3 2, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I33256026"]},{"raw_affiliation_string":"Saarland University, Campus D3 2, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5075345053"],"corresponding_institution_ids":["https://openalex.org/I33256026","https://openalex.org/I91712215"],"apc_list":{"value":3090,"currency":"USD","value_usd":3090},"apc_paid":{"value":3090,"currency":"USD","value_usd":3090},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19844389,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"2","first_page":"551","last_page":"563"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.7074999809265137,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.7074999809265137,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.052299998700618744,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.05209999904036522,"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/leverage","display_name":"Leverage (statistics)","score":0.5634999871253967},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.550000011920929},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44200000166893005},{"id":"https://openalex.org/keywords/flagging","display_name":"Flagging","score":0.40139999985694885},{"id":"https://openalex.org/keywords/equivalence","display_name":"Equivalence (formal languages)","score":0.4004000127315521},{"id":"https://openalex.org/keywords/singleton","display_name":"Singleton","score":0.36890000104904175},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.36059999465942383},{"id":"https://openalex.org/keywords/coverage-probability","display_name":"Coverage probability","score":0.3564000129699707},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.3528999984264374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7329000234603882},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5634999871253967},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5507000088691711},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.550000011920929},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46470001339912415},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44200000166893005},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43209999799728394},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.40139999985694885},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C117354338","wikidata":"https://www.wikidata.org/wiki/Q1165112","display_name":"Singleton","level":3,"score":0.36890000104904175},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C2776292839","wikidata":"https://www.wikidata.org/wiki/Q5179217","display_name":"Coverage probability","level":3,"score":0.3564000129699707},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C53811970","wikidata":"https://www.wikidata.org/wiki/Q5062194","display_name":"Centrality","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C103402496","wikidata":"https://www.wikidata.org/wiki/Q1106171","display_name":"Prediction interval","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2831999957561493},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28220000863075256},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C48105269","wikidata":"https://www.wikidata.org/wiki/Q1141160","display_name":"Header","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10032-026-00572-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-026-00572-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-026-00572-y.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10032-026-00572-y","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10032-026-00572-y","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10032-026-00572-y.pdf","source":{"id":"https://openalex.org/S90108747","display_name":"International Journal on Document Analysis and Recognition (IJDAR)","issn_l":"1433-2825","issn":["1433-2825","1433-2833"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Document Analysis and Recognition (IJDAR)","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4836004926","display_name":null,"funder_award_id":"01IS23064","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7134809188.pdf","grobid_xml":"https://content.openalex.org/works/W7134809188.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W2891117443","https://openalex.org/W2898700358","https://openalex.org/W2922714365","https://openalex.org/W2997154779","https://openalex.org/W3003484198","https://openalex.org/W3034864438","https://openalex.org/W3176851559","https://openalex.org/W3210790666","https://openalex.org/W4361793541","https://openalex.org/W4385478229","https://openalex.org/W4385574075","https://openalex.org/W4388901708","https://openalex.org/W4402683733","https://openalex.org/W4405178477","https://openalex.org/W4413060449"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Key":[1],"Information":[2],"Extraction":[3],"(KIE)":[4],"systems":[5],"based":[6],"on":[7,19,52],"Deep":[8],"Learning":[9],"achieve":[10],"strong":[11],"token-level":[12],"performance":[13],"but":[14],"offer":[15],"no":[16],"formal":[17],"guarantees":[18],"prediction":[20,70],"reliability,":[21,120],"limiting":[22],"their":[23],"adoption":[24],"in":[25],"business-critical":[26],"document":[27],"workflows.":[28],"In":[29],"this":[30],"work,":[31],"we":[32,57,163],"introduce":[33],"a":[34,53,59,74],"post":[35],"hoc":[36],"Uncertainty":[37],"Quantification":[38],"framework":[39],"for":[40,87,159,182],"KIE":[41],"using":[42],"Split":[43],"Conformal":[44],"Prediction":[45],"(CP).":[46],"After":[47],"fine-tuning":[48],"multimodal":[49],"transformer":[50],"models":[51],"challenging":[54],"receipt":[55],"dataset,":[56],"reserve":[58],"held-out":[60],"calibration":[61],"set":[62],"to":[63],"derive":[64],"nonconformity":[65],"scores":[66],"and":[67,112,136,143,150,178,190],"construct":[68],"entity-level":[69],"sets":[71,117,135],"that":[72,105,147],"satisfy":[73],"user-specified":[75],"error":[76],"rate.":[77],"On":[78],"unseen":[79],"receipts,":[80],"CP":[81,154],"achieves":[82],"tight":[83],"marginal":[84],"coverage":[85],"(98.3%":[86],"$$\\alpha":[88],"=0.02$$":[89],"\u03b1":[90],"=":[91],"0.02":[92],"),":[93],"with":[94,118],"70%":[95],"of":[96,193],"predictions":[97],"being":[98],"high-confidence":[99,176],"singletons.":[100],"A":[101],"detailed":[102],"analysis":[103],"shows":[104],"highly":[106],"structured":[107],"fields":[108,126],"such":[109,127],"as":[110,128],"dates":[111],"prices":[113],"yield":[114],"small,":[115],"singleton":[116],"near\u2013perfect":[119],"whereas":[121],"rare":[122],"or":[123,130],"semantically":[124],"ambiguous":[125],"tips":[129],"generic":[131],"keywords":[132],"produce":[133],"larger":[134],"lower":[137],"coverage.":[138],"By":[139],"exposing":[140],"positional":[141],"biases":[142],"common":[144],"label":[145],"confusions":[146],"standard":[148],"F1-scores":[149],"document-accuracy":[151],"metrics":[152],"overlook,":[153],"reveals":[155],"critical":[156],"risk":[157],"areas":[158],"downstream":[160],"automation.":[161],"Finally,":[162],"demonstrate":[164],"how":[165],"calibrated":[166],"prediction-set":[167],"sizes":[168],"can":[169],"drive":[170],"risk-aware":[171],"workflows":[172],"by":[173],"automatically":[174],"processing":[175],"extractions":[177],"flagging":[179],"uncertain":[180],"cases":[181],"human":[183],"review,":[184],"thereby":[185],"enhancing":[186],"the":[187],"efficiency,":[188],"trustworthiness":[189],"operational":[191],"feasibility":[192],"real-world":[194],"document-processing":[195],"systems.":[196]},"counts_by_year":[],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2026-03-11T00:00:00"}