{"id":"https://openalex.org/W7162111833","doi":"https://doi.org/10.48550/arxiv.2605.22413","title":"From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding","display_name":"From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding","publication_year":2026,"publication_date":"2026-05-21","ids":{"openalex":"https://openalex.org/W7162111833","doi":"https://doi.org/10.48550/arxiv.2605.22413"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.22413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22413","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.22413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136732772","display_name":"Yandi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yandi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136745298","display_name":"Libin Zhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhan, Libin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136794866","display_name":"Ziwei Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Ziwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126826586","display_name":"Tiancheng Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Tiancheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136756443","display_name":"Yuxuan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Yuxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136789210","display_name":"Wang Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063264979","display_name":"Leilei Gan","orcid":"https://orcid.org/0000-0001-5859-2588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Leilei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136802180","display_name":"jun chen","orcid":"https://orcid.org/0009-0002-0309-333X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4909999966621399,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4909999966621399,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.31119999289512634,"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":0.0731000006198883,"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/benchmarking","display_name":"Benchmarking","score":0.6642000079154968},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.4830999970436096},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.43459999561309814},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.4058000147342682},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.39340001344680786},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.37689998745918274},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.373199999332428},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3553999960422516},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.35100001096725464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7930999994277954},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6642000079154968},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4950999915599823},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.4830999970436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593000113964081},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.43459999561309814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4108000099658966},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36039999127388},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.33390000462532043},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3005000054836273},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C197947376","wikidata":"https://www.wikidata.org/wiki/Q5155608","display_name":"Comparability","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.22413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22413","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.22413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.22413","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Extracting":[0],"structured":[1],"information":[2,64],"from":[3,30,92],"visual":[4],"documents":[5],"(Visual":[6],"Information":[7],"Extraction,":[8],"VIE)":[9],"is":[10],"a":[11,54,106],"cornerstone":[12],"of":[13,59],"business":[14],"automation.":[15],"While":[16],"recent":[17],"Multimodal":[18],"Large":[19],"Language":[20],"Models":[21],"(MLLMs)":[22],"have":[23],"shown":[24],"promising":[25],"capabilities,":[26],"existing":[27],"benchmarks":[28],"suffer":[29],"critical":[31],"limitations":[32],"in":[33],"scale":[34],"and":[35,40,94,151],"realism,":[36],"lack":[37],"semantic":[38],"granularity,":[39],"fail":[41],"to":[42,126],"cover":[43],"diverse":[44,61],"document":[45],"types.":[46],"To":[47],"bridge":[48],"this":[49],"gap,":[50],"we":[51,104],"introduce":[52],"ReceiptBench,":[53],"large-scale,":[55],"human-annotated":[56],"benchmark":[57],"consisting":[58],"10k":[60],"receipts,":[62],"organizing":[63],"extraction":[65],"into":[66,122],"four":[67],"hierarchical":[68],"sub-tasks:":[69],"(1)":[70],"Basic":[71],"Perception":[72],"for":[73,80,88,98],"raw":[74],"text":[75],"spotting,":[76],"(2)":[77],"Format":[78],"Normalization":[79],"strictly":[81],"following":[82],"standardization":[83],"instructions,":[84],"(3)":[85],"Semantic":[86],"Reasoning":[87],"inferring":[89],"implicit":[90],"attributes":[91],"context,":[93],"(4)":[95],"Structure":[96],"Parsing":[97],"handling":[99],"nested":[100],"line":[101],"items.":[102],"Furthermore,":[103],"propose":[105],"two-stage":[107],"training":[108],"framework":[109],"incorporating":[110],"Metric-Aware":[111],"Group":[112],"Relative":[113],"Policy":[114],"Optimization":[115],"(GRPO),":[116],"which":[117],"translates":[118],"rigorous":[119],"evaluation":[120],"constraints":[121],"reinforcement":[123],"learning":[124],"signals":[125],"enhance":[127],"structural":[128],"consistency.":[129],"Extensive":[130],"experiments":[131],"demonstrate":[132],"that":[133],"our":[134,149],"method":[135],"yields":[136],"state-of-the-art":[137],"performance,":[138],"surpassing":[139],"leading":[140],"proprietary":[141],"models":[142],"on":[143],"complex":[144],"reasoning":[145],"tasks.":[146],"We":[147],"release":[148],"datasets":[150],"code":[152],"at":[153],"https://github.com/wwwT0ri/ReceiptBench.":[154]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}