{"id":"https://openalex.org/W4415428449","doi":"https://doi.org/10.3233/faia251296","title":"SARSum: A Relevance and Comprehensiveness-Aware Abstractive Summarization Dataset for Suspicious Activity Reports","display_name":"SARSum: A Relevance and Comprehensiveness-Aware Abstractive Summarization Dataset for Suspicious Activity Reports","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415428449","doi":"https://doi.org/10.3233/faia251296"},"language":null,"primary_location":{"id":"doi:10.3233/faia251296","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251296","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251296","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104218445","display_name":"Jean V. Alves","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jean V. Alves","raw_affiliation_strings":["Feedzai"],"affiliations":[{"raw_affiliation_string":"Feedzai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094134816","display_name":"Javier Li\u00e9bana","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Li\u00e9bana","raw_affiliation_strings":["Feedzai"],"affiliations":[{"raw_affiliation_string":"Feedzai","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064099361","display_name":"Hugo Ferreira","orcid":"https://orcid.org/0000-0003-2643-618X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hugo Ferreira","raw_affiliation_strings":["Feedzai"],"affiliations":[{"raw_affiliation_string":"Feedzai","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077752651","display_name":"Pedro Bizarro","orcid":"https://orcid.org/0000-0001-5281-1970"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro Bizarro","raw_affiliation_strings":["Feedzai"],"affiliations":[{"raw_affiliation_string":"Feedzai","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5104218445"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.58079169,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9700000286102295,"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/T10028","display_name":"Topic Modeling","score":0.9670000076293945,"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/automatic-summarization","display_name":"Automatic summarization","score":0.9212999939918518},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.8677999973297119},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.6657000184059143},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.595300018787384},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5012000203132629},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.42320001125335693}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.9212999939918518},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.8677999973297119},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7110999822616577},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6657000184059143},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.595300018787384},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.550599992275238},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5012000203132629},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.42320001125335693},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C134714966","wikidata":"https://www.wikidata.org/wiki/Q6934448","display_name":"Multi-document summarization","level":3,"score":0.32260000705718994},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.30640000104904175},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2703999876976013},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2776639384","wikidata":"https://www.wikidata.org/wiki/Q840396","display_name":"Ideal (ethics)","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/faia251296","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251296","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.3233/faia251296","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251296","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"benchmarks":[1],"that":[2,155,229],"evaluate":[3,82,190,286],"the":[4,34,47,58,83,94,128,135,144,152,200,230,244,274],"ability":[5,201],"of":[6,85,96,120,130,143,147,171,202,215,247,257,276],"Large":[7],"Language":[8],"Models":[9],"(LLMs)":[10],"to":[11,21,40,49,60,81,109,189,205,217,285],"summarize":[12],"rely":[13],"primarily":[14],"on":[15,25],"measuring":[16],"a":[17,22,43,78,98,103,193,213,241,251,260],"summary\u2019s":[18,44,194],"lexical":[19],"similarity":[20],"reference":[23,252],"or":[24,116,181],"assessing":[26],"whether":[27],"its":[28],"claims":[29],"are":[30,64,210,233],"factually":[31],"consistent":[32],"with":[33,164,254,263],"source":[35],"document.":[36],"These":[37,185,208,271],"approaches":[38],"fail":[39],"account":[41],"for":[42,265],"comprehensiveness":[45,68,137],"\u2014":[46,57],"extent":[48,59],"which":[50,61],"it":[51],"captures":[52],"important":[53],"information,":[54],"and":[55,69,138,196,225,236,250,283,288],"relevance":[56,70,195,287],"unessential":[62],"elements":[63,272],"omitted.":[65],"To":[66,127],"bolster":[67],"evaluation":[71],"in":[72,159],"high-stakes":[73,269],"domains,":[74],"we":[75,226],"propose":[76],"SARSum,":[77],"dataset":[79],"tailored":[80],"summarization":[84,140],"notes":[86,148],"taken":[87],"by":[88,106,151,176,221],"anti-money":[89],"laundering":[90],"(AML)":[91],"analysts":[92],"during":[93],"process":[95],"preparing":[97],"Suspicious":[99],"Activity":[100],"Report":[101],"(SAR),":[102],"document":[104],"filed":[105],"financial":[107],"institutions":[108],"alert":[110],"law":[111],"enforcement":[112],"about":[113],"suspicious":[114],"transactions":[115],"activities,":[117],"where":[118],"omission":[119],"key":[121,153,179,248],"details":[122],"can":[123],"be":[124,157],"extremely":[125],"costly.":[126],"best":[129],"our":[131],"knowledge,":[132],"SARSum":[133,239],"is":[134,149],"first":[136],"relevance-aware":[139],"dataset:":[141],"each":[142],"2,000":[145],"sets":[146],"accompanied":[150],"facts":[154,180,249],"must":[156],"retained":[158],"an":[160,222],"ideal":[161],"summary,":[162],"along":[163],"30":[165],"different":[166],"summaries":[167],"spanning":[168],"six":[169],"levels":[170,256],"information":[172],"selection":[173],"quality,":[174],"created":[175],"either":[177],"omitting":[178],"introducing":[182],"irrelevant":[183],"information.":[184],"resources":[186],"allow":[187],"practitioners":[188],"not":[191],"only":[192],"comprehensiveness,":[197],"but":[198],"also":[199],"automatic":[203],"metrics":[204],"assess":[206],"them.":[207],"instances":[209,232],"generated":[211],"using":[212],"variety":[214],"LLMs":[216],"rephrase":[218],"templates":[219],"approved":[220],"AML":[223],"expert,":[224],"empirically":[227],"verify":[228],"resulting":[231],"highly":[234],"abstractive":[235],"varied.":[237],"While":[238],"addresses":[240],"specific":[242],"domain,":[243],"novel":[245],"inclusion":[246],"set":[253],"known":[255],"quality":[258],"represents":[259],"crucial":[261],"step":[262],"potential":[264],"broader":[266],"application":[267],"across":[268],"scenarios.":[270],"enable":[273],"use":[275],"techniques":[277],"such":[278],"as":[279],"natural":[280],"language":[281],"inference":[282],"question-generation/question-answering":[284],"comprehensiveness.":[289]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}