{"id":"https://openalex.org/W7160138913","doi":"https://doi.org/10.63317/3b3zxy5qrw8s","title":"Efficient Financial Language Understanding via Distillation with Synthetic Data","display_name":"Efficient Financial Language Understanding via Distillation with Synthetic Data","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160138913","doi":"https://doi.org/10.63317/3b3zxy5qrw8s"},"language":null,"primary_location":{"id":"doi:10.63317/3b3zxy5qrw8s","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3b3zxy5qrw8s","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.18875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135283107","display_name":"Wen-Fong (Xavier) Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen-Fong (Xavier) Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135129389","display_name":"Edwin Simpson","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Edwin Simpson","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48318482,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10242","last_page":"10254"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.5938000082969666,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.5938000082969666,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11653","display_name":"Financial Distress and Bankruptcy Prediction","score":0.048500001430511475,"subfield":{"id":"https://openalex.org/subfields/1402","display_name":"Accounting"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","score":0.021299999207258224,"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/synthetic-data","display_name":"Synthetic data","score":0.4997999966144562},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4438999891281128},{"id":"https://openalex.org/keywords/production","display_name":"Production (economics)","score":0.37139999866485596},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.32739999890327454},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.24819999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5701000094413757},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3856000006198883},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.37139999866485596},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27889999747276306},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.2621999979019165},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.24819999933242798},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2460000067949295}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/3b3zxy5qrw8s","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3b3zxy5qrw8s","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.18875","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.18875","pdf_url":"https://arxiv.org/pdf/2606.18875","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.18875","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.18875","pdf_url":"https://arxiv.org/pdf/2606.18875","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160138913.pdf","grobid_xml":"https://content.openalex.org/works/W7160138913.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"instruction-following":[1],"models":[2,105],"are":[3,15,62],"powerful":[4],"but":[5],"costly":[6],"to":[7,44,78,106],"deploy,":[8],"particularly":[9],"in":[10,152],"finance,":[11],"where":[12,55],"labelled":[13,65],"data":[14,99],"limited":[16],"by":[17,66],"confidentiality":[18],"and":[19,64,74,118],"expert":[20],"annotation":[21],"cost.":[22],"We":[23],"present":[24],"an":[25],"efficient":[26],"framework":[27,49,69,143],"for":[28,52,81],"financial":[29,153],"sentiment":[30],"analysis":[31],"through":[32],"distillation":[33],"with":[34,110,155],"synthetic":[35,83,98],"data,":[36],"transferring":[37],"knowledge":[38],"from":[39],"a":[40,56,115,145],"large":[41],"instruction-tuned":[42],"teacher":[43,134],"compact":[45,104,123],"student":[46],"models.":[47],"The":[48,68,142],"is":[50],"designed":[51],"low-resource":[53],"conditions,":[54],"small":[57],"set":[58],"of":[59],"real":[60],"examples":[61,73,84],"collected":[63],"hand.":[67],"then":[70],"clusters":[71,77],"the":[72,76,122,127,133],"uses":[75],"select":[79],"seeds":[80],"generating":[82],"via":[85],"structured":[86],"few-shot":[87],"prompting.":[88],"Experiments":[89],"show":[90],"that":[91],"clustering-based":[92],"seed":[93],"selection":[94],"yields":[95],"more":[96,116],"representative":[97],"than":[100],"random":[101],"sampling,":[102],"enabling":[103],"achieve":[107],"strong":[108],"performance":[109],"minimal":[111,156],"supervision.":[112],"Notably,":[113],"on":[114,126,139],"complex":[117],"noisy":[119],"text":[120],"domain,":[121],"model":[124],"trained":[125],"complete":[128],"synthetic-seed":[129],"corpus":[130],"even":[131],"outperforms":[132],"model,":[135],"while":[136],"remaining":[137],"competitive":[138],"formal":[140],"text.":[141],"provides":[144],"practical":[146],"route":[147],"toward":[148],"resource-efficient":[149],"domain":[150],"adaptation":[151],"NLP":[154],"human":[157],"labelling":[158],"effort.":[159]},"counts_by_year":[],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2026-05-05T00:00:00"}