{"id":"https://openalex.org/W7133300634","doi":"https://doi.org/10.48550/arxiv.2603.01778","title":"LLM-as-an-Annotator: Training Lightweight Models with LLM-Annotated Examples for Aspect Sentiment Tuple Prediction","display_name":"LLM-as-an-Annotator: Training Lightweight Models with LLM-Annotated Examples for Aspect Sentiment Tuple Prediction","publication_year":2026,"publication_date":"2026-03-02","ids":{"openalex":"https://openalex.org/W7133300634","doi":"https://doi.org/10.48550/arxiv.2603.01778"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.01778","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01778","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.2603.01778","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093323666","display_name":"Nils Constantin Hellwig","orcid":"https://orcid.org/0009-0000-7305-8797"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hellwig, Nils Constantin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088698198","display_name":"Jakob Fehle","orcid":"https://orcid.org/0009-0001-7845-9511"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fehle, Jakob","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014534985","display_name":"Udo Kruschwitz","orcid":"https://orcid.org/0000-0002-5503-0341"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kruschwitz, Udo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128035721","display_name":"Christian Wolff","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wolff, Christian","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":0.9768000245094299,"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":0.9768000245094299,"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/T12488","display_name":"Mental Health via Writing","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.003700000001117587,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6952000260353088},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6212999820709229},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5267999768257141},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5098000168800354},{"id":"https://openalex.org/keywords/sentiment-analysis","display_name":"Sentiment analysis","score":0.47589999437332153},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.47350001335144043},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.396699994802475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8353999853134155},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6952000260353088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6539000272750854},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6212999820709229},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5446000099182129},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5098000168800354},{"id":"https://openalex.org/C66402592","wikidata":"https://www.wikidata.org/wiki/Q2271421","display_name":"Sentiment analysis","level":2,"score":0.47589999437332153},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.47589999437332153},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.47350001335144043},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.396699994802475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C44572571","wikidata":"https://www.wikidata.org/wiki/Q7448970","display_name":"SemEval","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.01778","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01778","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.2603.01778","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.01778","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":[{"score":0.8843348622322083,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Training":[0],"models":[1,36],"for":[2,37,48,88,106],"Aspect-Based":[3],"Sentiment":[4,51,56],"Analysis":[5],"(ABSA)":[6],"tasks":[7],"requires":[8],"manually":[9],"annotated":[10,86],"data,":[11,98],"which":[12],"is":[13],"expensive":[14],"and":[15,54,67],"time-consuming":[16],"to":[17,33,92],"obtain.":[18],"This":[19],"paper":[20],"introduces":[21],"LA-ABSA,":[22],"a":[23],"novel":[24],"approach":[25,44,61],"that":[26],"leverages":[27],"Large":[28],"Language":[29],"Model":[30],"(LLM)-generated":[31],"annotations":[32],"fine-tune":[34],"lightweight":[35],"complex":[38],"ABSA":[39],"tasks.":[40],"We":[41],"evaluate":[42],"our":[43],"on":[45,108],"five":[46],"datasets":[47],"Target":[49],"Aspect":[50,55],"Detection":[52],"(TASD)":[53],"Quad":[57],"Prediction":[58],"(ASQP).":[59],"Our":[60],"outperformed":[62],"previously":[63],"reported":[64],"augmentation":[65],"strategies":[66],"achieved":[68,100],"competitive":[69],"performance":[70,116],"with":[71,120],"LLM-prompting":[72],"in":[73],"low-resource":[74],"scenarios,":[75],"while":[76,123],"providing":[77],"substantial":[78],"energy":[79],"efficiency":[80],"benefits.":[81],"For":[82],"example,":[83],"using":[84],"50":[85],"examples":[87],"in-context":[89],"learning":[90],"(ICL)":[91],"guide":[93],"the":[94,109,115],"annotation":[95],"of":[96,104,117],"unlabeled":[97],"LA-ABSA":[99],"an":[101],"F1":[102],"score":[103],"49.85":[105],"ASQP":[107],"SemEval":[110],"Rest16":[111],"dataset,":[112],"closely":[113],"matching":[114],"ICL":[118],"prompting":[119],"Gemma-3-27B":[121],"(51.10),":[122],"requiring":[124],"significantly":[125],"lower":[126],"computational":[127],"resources.":[128]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-04T00:00:00"}