{"id":"https://openalex.org/W4408354806","doi":"https://doi.org/10.1109/icassp49660.2025.10889045","title":"Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset","display_name":"Extract Information from Hybrid Long Documents Leveraging LLMs: A Framework and Dataset","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354806","doi":"https://doi.org/10.1109/icassp49660.2025.10889045"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051815372","display_name":"Chongjian Yue","orcid":"https://orcid.org/0009-0009-2166-802X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Chongjian Yue","raw_affiliation_strings":["Peking University,School of Software & Microelectronics,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University,School of Software & Microelectronics,Beijing,China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104264437","display_name":"Xinrun Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinrun Xu","raw_affiliation_strings":["Institute of Software,Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100957906","display_name":"Xiaojun Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Ma","raw_affiliation_strings":["Microsoft,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008387608","display_name":"Lun Du","orcid":"https://orcid.org/0000-0002-7625-0650"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lun Du","raw_affiliation_strings":["Ant Group,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ant Group,Beijing,China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057841485","display_name":"Zhiming Ding","orcid":"https://orcid.org/0000-0002-2057-5325"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiming Ding","raw_affiliation_strings":["Institute of Software,Chinese Academy of Sciences,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Software,Chinese Academy of Sciences,Beijing,China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006300825","display_name":"Shi Han","orcid":"https://orcid.org/0000-0002-0360-6089"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Han","raw_affiliation_strings":["Microsoft,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101567180","display_name":"Dongmei Zhang","orcid":"https://orcid.org/0000-0001-6302-0373"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Zhang","raw_affiliation_strings":["Microsoft,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049552955","display_name":"Qi Zhang","orcid":"https://orcid.org/0000-0001-6444-5314"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["Microsoft,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Beijing,China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5051815372"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":4.9011,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93974807,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.9646999835968018,"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"}},"topics":[{"id":"https://openalex.org/T14330","display_name":"Library Science and Information Systems","score":0.9646999835968018,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9355000257492065,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.9305999875068665,"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/computer-science","display_name":"Computer science","score":0.6438774466514587},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4402603209018707},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3953455090522766}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6438774466514587},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4402603209018707},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3953455090522766}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889045","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889045","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W2970641574","https://openalex.org/W2974498669","https://openalex.org/W3034910758","https://openalex.org/W3105607850","https://openalex.org/W3166125679","https://openalex.org/W3174986053","https://openalex.org/W4205508242","https://openalex.org/W4313007903","https://openalex.org/W4384642600","https://openalex.org/W4385571437","https://openalex.org/W4386566488","https://openalex.org/W4389523710","https://openalex.org/W4389539730","https://openalex.org/W4391583900","https://openalex.org/W4393161130","https://openalex.org/W4398765347","https://openalex.org/W4404781729","https://openalex.org/W4411120260","https://openalex.org/W6809646742","https://openalex.org/W6838865847","https://openalex.org/W6838941467","https://openalex.org/W6840738256","https://openalex.org/W6850671237","https://openalex.org/W6851788146","https://openalex.org/W6852622455","https://openalex.org/W6862186891","https://openalex.org/W6862475336","https://openalex.org/W6873894331","https://openalex.org/W6888069211"],"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":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"demonstrate":[4],"exceptional":[5],"performance":[6],"in":[7,35,117,138,161],"textual":[8,24],"understanding":[9],"and":[10,19,25,67,90,140,156],"tabular":[11,26],"reasoning":[12],"tasks.":[13],"However,":[14],"their":[15],"ability":[16],"to":[17,60,63,71,88,108,126],"comprehend":[18],"analyze":[20],"hybrid":[21,31,39],"text,":[22],"containing":[23],"data,":[27],"remains":[28],"unexplored.":[29],"The":[30,85,112,122,154],"text":[32],"often":[33],"appears":[34],"the":[36,46,65,82,92,133,147,162],"form":[37],"of":[38,49,76,95,135],"long":[40],"documents":[41],"(HLDs),":[42],"which":[43],"far":[44],"exceed":[45],"token":[47],"limit":[48],"LLMs.":[50],"Consequently,":[51],"we":[52,144],"apply":[53],"an":[54],"Automated":[55],"Information":[56],"Extraction":[57,151],"framework":[58],"(AIE)":[59],"enable":[61],"LLMs":[62,107,128],"process":[64],"HLDs":[66,139],"carry":[68],"out":[69],"experiments":[70],"analyse":[72],"four":[73],"important":[74],"aspects":[75],"information":[77],"extraction":[78],"from":[79],"HLDs.":[80,130],"Given":[81],"findings:":[83],"1)":[84],"effective":[86],"way":[87,103],"select":[89],"summarize":[91],"useful":[93,123],"part":[94],"a":[96],"HLD.":[97],"2)":[98],"An":[99],"easy":[100],"table":[101],"serialization":[102],"is":[104],"enough":[105],"for":[106],"understand":[109],"tables.":[110],"3)":[111],"naive":[113],"AIE":[114],"has":[115],"adaptability":[116],"many":[118],"complex":[119],"scenarios.":[120],"4)":[121],"prompt":[124],"engineering":[125],"enhance":[127],"on":[129],"To":[131],"address":[132],"issue":[134],"dataset":[136,155],"scarcity":[137],"support":[141],"future":[142],"work,":[143],"also":[145],"propose":[146],"Financial":[148],"Reports":[149],"Numerical":[150],"(FINE)":[152],"dataset.":[153],"code":[157],"are":[158],"publicly":[159],"available":[160],"attachments.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-03T09:05:47.796612","created_date":"2025-10-10T00:00:00"}