{"id":"https://openalex.org/W7166026291","doi":"https://doi.org/10.48550/arxiv.2606.26571","title":"Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning","display_name":"Zero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning","publication_year":2026,"publication_date":"2026-06-25","ids":{"openalex":"https://openalex.org/W7166026291","doi":"https://doi.org/10.48550/arxiv.2606.26571"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.26571","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26571","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2606.26571","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126420301","display_name":"Y Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yiju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139448433","display_name":"Wenxian Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wenxian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100747270","display_name":"Lijun Zhou","orcid":"https://orcid.org/0009-0003-6079-7349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Lijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139431788","display_name":"Rui Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123068639","display_name":"Xiao Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan, Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139450878","display_name":"Tao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139453772","display_name":"Haizhou Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Haizhou","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":0.46239998936653137,"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":0.46239998936653137,"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":0.12189999967813492,"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/T11147","display_name":"Misinformation and Its Impacts","score":0.10989999771118164,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7095000147819519},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6352999806404114},{"id":"https://openalex.org/keywords/chaining","display_name":"Chaining","score":0.5979999899864197},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5843999981880188},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5706999897956848},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5454000234603882},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.544700026512146},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.37299999594688416},{"id":"https://openalex.org/keywords/backward-chaining","display_name":"Backward chaining","score":0.3472999930381775}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318000197410583},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7095000147819519},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6352999806404114},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5843999981880188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835999846458435},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.544700026512146},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39340001344680786},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.37299999594688416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.351500004529953},{"id":"https://openalex.org/C129916263","wikidata":"https://www.wikidata.org/wiki/Q1141183","display_name":"Backward chaining","level":4,"score":0.3472999930381775},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2776289891","wikidata":"https://www.wikidata.org/wiki/Q1931511","display_name":"Neglect","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C56814567","wikidata":"https://www.wikidata.org/wiki/Q1323686","display_name":"Explicit knowledge","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C2780876879","wikidata":"https://www.wikidata.org/wiki/Q3054749","display_name":"Meaning (existential)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.2782000005245209},{"id":"https://openalex.org/C142614401","wikidata":"https://www.wikidata.org/wiki/Q777433","display_name":"Forward chaining","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C115925183","wikidata":"https://www.wikidata.org/wiki/Q1412694","display_name":"Knowledge-based systems","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2776802673","wikidata":"https://www.wikidata.org/wiki/Q1548396","display_name":"Relevance theory","level":3,"score":0.2671999931335449},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26100000739097595},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.26571","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26571","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.26571","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.26571","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7367976903915405}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Zero-shot":[0],"tweet-level":[1,96],"stance":[2,73,99,107],"detection":[3,108],"confronts":[4],"two":[5],"primary":[6],"challenges:":[7],"(1)":[8],"mitigating":[9],"the":[10,20,39,56,62,93,127],"context":[11],"sparsity":[12],"inherent":[13],"in":[14,54],"short":[15],"texts,":[16],"and":[17,25,71,120,134,145,165,180,197,199,204],"(2)":[18],"establishing":[19],"relevance":[21,57],"between":[22,69],"implicit":[23,147],"targets":[24,60],"textual":[26,137],"content.":[27],"While":[28],"existing":[29],"methods":[30],"primarily":[31],"focus":[32],"on":[33,177,195,202],"incorporating":[34],"external":[35,112],"knowledge,":[36,90],"they":[37],"neglect":[38],"intrinsic":[40],"semantic":[41],"cues":[42],"embedded":[43],"within":[44],"key":[45,136],"intra-textual":[46],"entities.":[47],"Furthermore,":[48],"current":[49],"models":[50],"exhibit":[51],"limited":[52],"capability":[53],"determining":[55],"of":[58,192],"unseen":[59],"to":[61,67,132,161],"given":[63],"text,":[64],"thereby":[65],"struggling":[66],"differentiate":[68],"\"neutral\"":[70,152],"\"irrelevant\"":[72,154],"labels.":[74],"To":[75,88,149],"address":[76],"these":[77],"issues,":[78],"we":[79,156],"first":[80,94],"construct":[81],"a":[82,105,167],"four-class,":[83],"multi-topic":[84],"Japanese":[85,95],"tweet":[86],"dataset.":[87],"our":[89],"this":[91],"is":[92],"dataset":[97],"for":[98,117,124,172],"detection.":[100],"We":[101],"then":[102],"propose":[103],"KIRP,":[104],"zero-shot":[106],"framework.":[109],"It":[110],"integrates":[111],"knowledge":[113,130],"with":[114],"entity":[115],"reorganization":[116],"data":[118],"augmentation":[119],"employs":[121],"prompt":[122],"chaining":[123],"reasoning.":[125],"Specifically,":[126],"framework":[128],"incorporates":[129],"graphs":[131],"supplement":[133],"reorganize":[135],"entities,":[138],"while":[139],"reflective":[140],"Chain-of-Thought":[141],"(CoT)":[142],"reasoning":[143],"extracts":[144],"validates":[146],"targets.":[148],"better":[150],"distinguish":[151],"from":[153],"labels,":[155],"adopt":[157],"stance-aware":[158],"contrastive":[159],"learning":[160],"capture":[162],"discriminative":[163],"features":[164],"design":[166],"three-layer":[168],"iterative":[169],"prototype":[170],"network":[171],"fine-grained":[173],"classification.":[174],"Experimental":[175],"results":[176],"SemEval-2016,":[178,196],"WT-WT,":[179],"KIRP-D":[181],"show":[182],"that":[183],"KIRP":[184,188],"achieves":[185],"state-of-the-art":[186],"performance.":[187],"obtains":[189],"F1":[190],"scores":[191],"84.05%":[193],"(three-class)":[194],"84.99%":[198],"79.18%":[200],"(four-class)":[201],"WT-WT":[203],"KIRP-D,":[205],"respectively.":[206]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-27T00:00:00"}