{"id":"https://openalex.org/W4415443980","doi":"https://doi.org/10.1109/tkde.2025.3623941","title":"Multi-Task Learning With LLMs for Implicit Sentiment Analysis: Data-Level and Task-Level Automatic Weight Learning","display_name":"Multi-Task Learning With LLMs for Implicit Sentiment Analysis: Data-Level and Task-Level Automatic Weight Learning","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4415443980","doi":"https://doi.org/10.1109/tkde.2025.3623941"},"language":null,"primary_location":{"id":"doi:10.1109/tkde.2025.3623941","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3623941","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/tkde.2025.3623941","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113280418","display_name":"Wenna Lai","orcid":"https://orcid.org/0009-0009-5169-5256"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenna Lai","raw_affiliation_strings":["Department of Computing, Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0009-5169-5256","affiliations":[{"raw_affiliation_string":"Department of Computing, Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013151488","display_name":"Haoran Xie","orcid":"https://orcid.org/0000-0003-0965-3617"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoran Xie","raw_affiliation_strings":["School of Data Science, Lingnan University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-0965-3617","affiliations":[{"raw_affiliation_string":"School of Data Science, Lingnan University, Hong Kong","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051512158","display_name":"Guandong Xu","orcid":"https://orcid.org/0000-0003-4493-6663"},"institutions":[{"id":"https://openalex.org/I114017466","display_name":"University of Technology Sydney","ror":"https://ror.org/03f0f6041","country_code":"AU","type":"education","lineage":["https://openalex.org/I114017466"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guandong Xu","raw_affiliation_strings":["School of Computer Science and the Data Science Institute, University of Technology Sydney, Sydney, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0003-4493-6663","affiliations":[{"raw_affiliation_string":"School of Computer Science and the Data Science Institute, University of Technology Sydney, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I114017466"]}]},{"author_position":"last","author":{"id":null,"display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qing Li","raw_affiliation_strings":["Department of Computing, Hong Kong Polytechnic University, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-3370-471X","affiliations":[{"raw_affiliation_string":"Department of Computing, Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.792,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91908415,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"38","issue":"1","first_page":"506","last_page":"517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9010999798774719,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9010999798774719,"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/salient","display_name":"Salient","score":0.6563000082969666},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5683000087738037},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5540000200271606},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5302000045776367},{"id":"https://openalex.org/keywords/homoscedasticity","display_name":"Homoscedasticity","score":0.5092999935150146},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5047000050544739},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.3686999976634979},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.36550000309944153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7454000115394592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.656499981880188},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6563000082969666},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5683000087738037},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5540000200271606},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5440999865531921},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5302000045776367},{"id":"https://openalex.org/C104409967","wikidata":"https://www.wikidata.org/wiki/Q1054836","display_name":"Homoscedasticity","level":3,"score":0.5092999935150146},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5047000050544739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.3686999976634979},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C2777541608","wikidata":"https://www.wikidata.org/wiki/Q5165194","display_name":"Contextual learning","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C166998942","wikidata":"https://www.wikidata.org/wiki/Q16969238","display_name":"Interactor","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C71611378","wikidata":"https://www.wikidata.org/wiki/Q5165191","display_name":"Contextual design","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.26080000400543213},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2025.3623941","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3623941","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/tkde.2025.3623941","is_oa":true,"landing_page_url":"https://doi.org/10.1109/tkde.2025.3623941","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2117130368","https://openalex.org/W2251648804","https://openalex.org/W2251890715","https://openalex.org/W2791248998","https://openalex.org/W2889191048","https://openalex.org/W2896457183","https://openalex.org/W2913340405","https://openalex.org/W2962833140","https://openalex.org/W2963677766","https://openalex.org/W2998446468","https://openalex.org/W3035529900","https://openalex.org/W3083435909","https://openalex.org/W3205661242","https://openalex.org/W3209701493","https://openalex.org/W3213193683","https://openalex.org/W4312908198","https://openalex.org/W4317568744","https://openalex.org/W4361732112","https://openalex.org/W4385570584","https://openalex.org/W4385571219","https://openalex.org/W4385571452","https://openalex.org/W4386566654","https://openalex.org/W4393146948","https://openalex.org/W4401042146","https://openalex.org/W4401042286","https://openalex.org/W4404780828","https://openalex.org/W4412158322"],"related_works":[],"abstract_inverted_index":{"Implicit":[0],"sentiment":[1,138],"analysis":[2],"(ISA)":[3],"presents":[4],"significant":[5],"challenges":[6],"due":[7],"to":[8,26,42,48,92,136,144,172],"the":[9,40,87,114,222],"absence":[10],"of":[11,45,66,90,119,169,203,226],"salient":[12],"cue":[13],"words.":[14],"Previous":[15],"methods":[16],"have":[17],"struggled":[18],"with":[19,34,192],"insufficient":[20],"data":[21,163],"and":[22,51,80,116,140,152,159,164,213,224],"limited":[23],"reasoning":[24,117,180],"capabilities":[25,118],"infer":[27],"underlying":[28],"opinions.":[29],"Integrating":[30],"multi-task":[31],"learning":[32,124],"(MTL)":[33],"large":[35],"language":[36],"models":[37,44,91,168,202],"(LLMs)":[38],"offers":[39],"potential":[41],"enable":[43],"varying":[46,88,170,204],"sizes":[47,171,205],"reliably":[49],"perceive":[50],"recognize":[52],"genuine":[53],"opinions":[54],"in":[55,76,216],"ISA.":[56],"However,":[57],"existing":[58],"MTL":[59,107,143],"approaches":[60],"are":[61,184,190],"constrained":[62],"by":[63,112],"two":[64],"sources":[65],"uncertainty:":[67],"<italic":[68,81,102,127,217],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[69,82,103,128,218],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">data-level":[70],"uncertainty</i>,":[71,84],"arising":[72],"from":[73,86],"hallucination":[74],"problems":[75],"LLM-generated":[77],"contextual":[78,94],"information,":[79],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">task-level":[83],"stemming":[85],"capacities":[89],"process":[93],"information.":[95],"To":[96],"handle":[97],"these":[98],"uncertainties,":[99],"we":[100],"propose":[101],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MT-ISA</i>,":[104],"a":[105],"novel":[106],"framework":[108],"that":[109,201],"enhances":[110],"ISA":[111],"leveraging":[113],"generation":[115],"LLMs":[120,135],"through":[121],"automatic":[122,142],"weight":[123],"(AWL).":[125],"Specifically,":[126],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MT-ISA</i>":[129],"constructs":[130],"auxiliary":[131,147,214],"tasks":[132,215],"using":[133],"generative":[134],"supplement":[137],"elements":[139],"incorporates":[141],"fully":[145],"exploit":[146],"data.":[148],"We":[149],"introduce":[150],"data-level":[151,187],"task-level":[153,196],"AWL,":[154,188],"which":[155,189],"dynamically":[156],"identify":[157],"relationships":[158],"prioritize":[160],"more":[161],"reliable":[162],"critical":[165],"tasks,":[166],"enabling":[167],"adaptively":[173],"learn":[174],"fine-grained":[175],"weights":[176],"based":[177],"on":[178],"their":[179],"capabilities.":[181],"Three":[182],"strategies":[183],"investigated":[185],"for":[186,195],"integrated":[191],"homoscedastic":[193],"uncertainty":[194],"AWL.":[197],"Extensive":[198],"experiments":[199],"reveal":[200],"achieve":[206],"an":[207],"optimal":[208],"balance":[209],"between":[210],"primary":[211],"prediction":[212],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">MT-ISA</i>.":[219],"This":[220],"underscores":[221],"effectiveness":[223],"adaptability":[225],"our":[227],"approach.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-24T00:00:00"}