{"id":"https://openalex.org/W7166854947","doi":"https://doi.org/10.18653/v1/2026.semeval-1.403","title":"RPI Team at SemEval-2026 Task 3: An LLM-Encoder Ensemble for Coarse-to-Fine Valence-Arousal Sentiment Prediction","display_name":"RPI Team at SemEval-2026 Task 3: An LLM-Encoder Ensemble for Coarse-to-Fine Valence-Arousal Sentiment Prediction","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166854947","doi":"https://doi.org/10.18653/v1/2026.semeval-1.403"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.semeval-1.403","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.semeval-1.403","pdf_url":"https://aclanthology.org/2026.semeval-1.403.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Workshop on Semantic Evaluation (2026)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.semeval-1.403.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092973318","display_name":"Mohammed Shahid Modi","orcid":"https://orcid.org/0009-0008-5509-5277"},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammed Shahid Modi","raw_affiliation_strings":["Rensselaer Polytechnic Institute Troy , New York , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute Troy , New York , USA","institution_ids":["https://openalex.org/I165799507"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105506403","display_name":"Boleslaw Szymanski","orcid":null},"institutions":[{"id":"https://openalex.org/I165799507","display_name":"Rensselaer Polytechnic Institute","ror":"https://ror.org/01rtyzb94","country_code":"US","type":"education","lineage":["https://openalex.org/I165799507"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boleslaw Szymanski","raw_affiliation_strings":["Rensselaer Polytechnic Institute Troy , New York , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rensselaer Polytechnic Institute Troy , New York , USA","institution_ids":["https://openalex.org/I165799507"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165799507"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88081224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3218","last_page":"3224"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.4383000135421753,"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"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.4383000135421753,"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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.3278000056743622,"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":0.07980000227689743,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6388999819755554},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.2689000070095062},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25929999351501465},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2515999972820282}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769999861717224},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6388999819755554},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5271999835968018},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3675000071525574},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3061000108718872},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25929999351501465},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2515999972820282},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.24609999358654022}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.semeval-1.403","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.semeval-1.403","pdf_url":"https://aclanthology.org/2026.semeval-1.403.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Workshop on Semantic Evaluation (2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.semeval-1.403","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.semeval-1.403","pdf_url":"https://aclanthology.org/2026.semeval-1.403.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Workshop on Semantic Evaluation (2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Gender equality","score":0.41228070855140686,"id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166854947.pdf","grobid_xml":"https://content.openalex.org/works/W7166854947.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"our":[2],"coarse-to-fine":[3],"Valence-Arousal":[4],"(VA)":[5],"ensemble":[6],"system":[7,111],"for":[8,77,104],"subtask":[9],"1":[10,35],"of":[11,23,116],"task":[12],"3":[13,26],"(DimABSA)":[14],"which":[15],"covers":[16],"aspect-level":[17],"VA":[18,40,67,115,127],"prediction.We":[19],"use":[20],"a":[21,56,96],"pair":[22],"trained":[24,83,89,135],"Qwen":[25],"8B":[27],"LoRA-tuned":[28],"LLMs":[29,84],"to":[30,64,129],"predict":[31],"coarse":[32],"bins":[33],"between":[34],"and":[36,85,109,121,132],"8,":[37],"providing":[38],"ordinal":[39],"guidance":[41,62,73],"signals":[42,74],"along":[43],"with":[44,55],"distributional":[45],"features.We":[46],"then":[47],"train":[48],"an":[49,113],"instruction-style,":[50],"multilingual":[51],"E5":[52],"encoder":[53,103],"model":[54,128],"multitask":[57],"head":[58],"using":[59],"these":[60],"LLM-derived":[61],"features":[63],"produce":[65],"continuous":[66],"predictions.At":[68],"inference":[69],"time,":[70],"the":[71,78,82,88,93,102,125],"same":[72],"are":[75],"generated":[76],"test":[79],"set":[80],"by":[81],"fed":[86],"into":[87],"encoder.This":[90],"approach":[91],"leverages":[92],"LLM":[94],"as":[95],"high-level":[97],"prior":[98],"while":[99],"relying":[100],"on":[101,136,147],"precise":[105],"calibration":[106],"across":[107,118],"languages":[108,120],"domains.Our":[110],"achieves":[112],"RMSE":[114],"1.20":[117],"six":[119],"five":[122],"domains.We":[123],"compare":[124],"joint":[126],"separated":[130],"valence":[131],"arousal":[133,148],"models":[134],"coarsened":[137],"ground":[138],"truth":[139],"data,":[140],"showing":[141],"that":[142],"it":[143],"outperforms":[144],"them,":[145],"particularly":[146],"correlations.":[149]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}