{"id":"https://openalex.org/W7154389095","doi":"https://doi.org/10.48550/arxiv.2604.10633","title":"ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction","display_name":"ProUIE: A Macro-to-Micro Progressive Learning Method for LLM-based Universal Information Extraction","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7154389095","doi":"https://doi.org/10.48550/arxiv.2604.10633"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.10633","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10633","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.2604.10633","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125379063","display_name":"Wenda Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Wenda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133609540","display_name":"Zhigang Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Zhigang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068044387","display_name":"Shuai Nie","orcid":"https://orcid.org/0000-0002-8078-6829"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123546030","display_name":"Guangyao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Guangyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123579663","display_name":"Lisung Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Lisung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133594471","display_name":"Binyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Binyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053853035","display_name":"Yaran Chen","orcid":"https://orcid.org/0000-0001-9356-0610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yaran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064575557","display_name":"Peng Zhou","orcid":"https://orcid.org/0000-0002-1140-4380"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133618858","display_name":"Hongzhen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Hongzhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133595355","display_name":"Yuchen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133562371","display_name":"Wenyue Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Wenyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133625276","display_name":"Jiaming Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jiaming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133573875","display_name":"Runyu Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Runyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133589828","display_name":"Ying Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Ying","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/T10028","display_name":"Topic Modeling","score":0.4465000033378601,"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/T10028","display_name":"Topic Modeling","score":0.4465000033378601,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.06260000169277191,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.05820000171661377,"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/information-extraction","display_name":"Information extraction","score":0.625},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.45739999413490295},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3711000084877014},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.3458999991416931},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.34040001034736633},{"id":"https://openalex.org/keywords/order","display_name":"Order (exchange)","score":0.3203999996185303},{"id":"https://openalex.org/keywords/incremental-learning","display_name":"Incremental learning","score":0.2892000079154968}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7702000141143799},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.625},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4950000047683716},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C2780735816","wikidata":"https://www.wikidata.org/wiki/Q28324931","display_name":"Incremental learning","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C2983203078","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Information gain","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.10633","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10633","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.2604.10633","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.10633","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":{"LLM-based":[0],"universal":[1],"information":[2,10,161],"extraction":[3,74],"(UIE)":[4],"methods":[5],"often":[6,21],"rely":[7],"on":[8,65,83,126,141],"additional":[9],"beyond":[11],"the":[12,66],"original":[13],"training":[14,18,68],"data,":[15],"which":[16,54,81,108],"increases":[17],"complexity":[19],"yet":[20],"yields":[22],"limited":[23],"gains.":[24],"To":[25],"address":[26],"this,":[27],"we":[28],"propose":[29],"ProUIE,":[30],"a":[31,72,149],"Macro-to-Micro":[32],"progressive":[33],"learning":[34],"approach":[35],"that":[36,131],"improves":[37,134],"UIE":[38],"without":[39],"introducing":[40],"any":[41],"external":[42],"information.":[43],"ProUIE":[44,132],"consists":[45],"of":[46],"three":[47],"stages:":[48],"(i)":[49],"macro-level":[50],"Complete":[51],"Modeling":[52],"(CM),":[53],"learns":[55],"NER,":[56],"RE,":[57],"and":[58,91,100,102,122,145,152],"EE":[59],"along":[60],"their":[61],"intrinsic":[62],"difficulty":[63],"order":[64],"full":[67],"data":[69,85],"to":[70,95,119],"build":[71],"unified":[73,135],"foundation,":[75],"(ii)":[76],"meso-level":[77],"Streamlined":[78],"Alignment":[79],"(SA),":[80],"operates":[82],"sampled":[84],"with":[86,111],"simplified":[87],"target":[88],"formats,":[89],"streamlining":[90],"regularizing":[92],"structured":[93],"outputs":[94],"make":[96],"them":[97],"more":[98],"concise":[99],"controllable,":[101],"(iii)":[103],"micro-level":[104],"Deep":[105],"Exploration":[106],"(DE),":[107],"applies":[109],"GRPO":[110],"stepwise":[112],"fine-grained":[113],"rewards":[114],"(SFR)":[115],"over":[116],"structural":[117],"units":[118],"guide":[120],"exploration":[121],"improve":[123],"performance.":[124],"Experiments":[125],"36":[127],"public":[128],"datasets":[129],"show":[130],"consistently":[133],"extraction,":[136],"outperforming":[137],"strong":[138],"instruction-tuned":[139],"baselines":[140],"average":[142],"for":[143],"NER":[144],"RE":[146],"while":[147],"using":[148],"smaller":[150],"backbone,":[151],"it":[153],"further":[154],"demonstrates":[155],"clear":[156],"gains":[157],"in":[158],"large-scale":[159],"production-oriented":[160],"extraction.":[162]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-15T00:00:00"}