{"id":"https://openalex.org/W7163001002","doi":"https://doi.org/10.48550/arxiv.2605.31446","title":"Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Triplet Extraction","display_name":"Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Triplet Extraction","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163001002","doi":"https://doi.org/10.48550/arxiv.2605.31446"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.31446","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31446","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.2605.31446","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115426610","display_name":"Wenna Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Wenna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137588175","display_name":"Haoran Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137540368","display_name":"Guandong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Guandong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137534284","display_name":"Qing Li","orcid":"https://orcid.org/0000-0003-3370-471X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124000546","display_name":"S. Joe Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, S. Joe","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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9876000285148621,"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":0.9876000285148621,"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":0.001500000013038516,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0008999999845400453,"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/leverage","display_name":"Leverage (statistics)","score":0.60589998960495},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5062000155448914},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5042999982833862},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.42660000920295715},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.38119998574256897},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.3564999997615814},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.35199999809265137}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7944999933242798},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.60589998960495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.553600013256073},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5062000155448914},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5042999982833862},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46860000491142273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4309999942779541},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38999998569488525},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38119998574256897},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.35199999809265137},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C111640148","wikidata":"https://www.wikidata.org/wiki/Q847349","display_name":"Rubric","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28110000491142273},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.31446","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31446","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.2605.31446","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31446","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":{"Aspect":[0],"Sentiment":[1],"Triplet":[2],"Extraction":[3],"(ASTE)":[4],"aims":[5],"to":[6,163,178,200],"identify":[7],"aspect":[8],"terms,":[9,11],"opinion":[10,28],"and":[12,32,76,123,134,145,152,155,167],"sentiment":[13],"polarities":[14],"as":[15,27,127,137,204],"structured":[16],"triplets,":[17],"providing":[18],"essential":[19],"inputs":[20],"for":[21,104],"downstream":[22],"information":[23],"system":[24],"applications":[25],"such":[26],"mining,":[29],"explainable":[30],"recommendations,":[31],"review":[33],"summarization.":[34],"Prior":[35],"work":[36],"mainly":[37],"focuses":[38],"on":[39],"end-to-end":[40],"extraction,":[41],"while":[42,67],"post":[43],"hoc":[44],"verification":[45,85,207],"of":[46,57],"extracted":[47],"triplets":[48,62,149],"remains":[49],"comparatively":[50],"underexplored.":[51],"This":[52],"gap":[53],"limits":[54],"the":[55,112,172],"reliability":[56],"ASTE":[58,189],"systems,":[59],"since":[60],"predicted":[61],"may":[63],"be":[64],"locally":[65],"plausible":[66,147],"being":[68],"globally":[69],"invalid.":[70],"Moreover,":[71],"candidate":[72,77,180],"invalidity":[73],"is":[74,79,114],"multi-faceted":[75],"usability":[78],"inherently":[80],"graded,":[81],"motivating":[82],"a":[83,102,205],"fine-grained":[84],"mechanism":[86],"that":[87,192],"can":[88],"filter":[89,179],"or":[90],"re-rank":[91],"outputs":[92],"from":[93],"diverse":[94],"extractors.":[95],"In":[96],"this":[97],"paper,":[98],"we":[99],"propose":[100],"FiVeD,":[101],"framework":[103],"Fine-grained":[105],"Verification":[106],"with":[107,116,130,160],"Diagnostic":[108],"reasoning":[109],"supervision.":[110],"Specifically,":[111],"verifier":[113],"trained":[115],"multiple":[117,188],"complementary":[118],"objectives,":[119],"including":[120],"validity":[121],"classification":[122,133],"quality":[124,165,174],"score":[125],"estimation":[126],"primary":[128],"tasks,":[129],"error":[131,143],"type":[132],"rationale":[135],"generation":[136],"auxiliary":[138],"tasks.":[139],"We":[140],"define":[141],"hierarchical":[142],"categories":[144],"construct":[146],"incorrect":[148],"under":[150],"semantic":[151],"syntactic":[153],"constraints,":[154],"leverage":[156],"an":[157],"off-the-shelf":[158],"LLM":[159],"task-specific":[161],"rubrics":[162],"produce":[164],"scores":[166,175],"diagnostic":[168],"rationales.":[169],"During":[170],"inference,":[171],"resulting":[173],"are":[176],"used":[177],"outputs,":[181],"supporting":[182],"adjustable":[183],"precision-recall":[184],"tradeoffs.":[185],"Experiments":[186],"across":[187],"baselines":[190],"demonstrate":[191],"FiVeD":[193],"consistently":[194],"improves":[195],"extraction":[196],"performance":[197],"by":[198],"up":[199],"3.53":[201],"F1":[202],"points":[203],"plug-and-play":[206],"module.":[208]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-02T00:00:00"}