{"id":"https://openalex.org/W7140113680","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.289","title":"Revealing the Numeracy Gap: An Empirical Investigation of Text Embedding Models","display_name":"Revealing the Numeracy Gap: An Empirical Investigation of Text Embedding Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140113680","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.289"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.289","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.289","pdf_url":"https://aclanthology.org/2026.findings-eacl.289.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.289.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130362017","display_name":"Ningyuan Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ningyuan Deng","raw_affiliation_strings":["Department of Information Systems, Business Statistics and Operations Management , HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Business Statistics and Operations Management , HKUST","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015874450","display_name":"Hanyu Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hanyu Duan","raw_affiliation_strings":["Department of Information Systems, Business Statistics and Operations Management , HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Business Statistics and Operations Management , HKUST","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130384670","display_name":"Yixuan Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixuan Tang","raw_affiliation_strings":["Department of Information Systems, Business Statistics and Operations Management , HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Business Statistics and Operations Management , HKUST","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130359603","display_name":"Yi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi Yang","raw_affiliation_strings":["Department of Information Systems, Business Statistics and Operations Management , HKUST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, Business Statistics and Operations Management , HKUST","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.3553527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5448","last_page":"5461"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.21709999442100525,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.21709999442100525,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.19429999589920044,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.0763000026345253,"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/empirical-research","display_name":"Empirical research","score":0.3824999928474426},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3781999945640564},{"id":"https://openalex.org/keywords/numeracy","display_name":"Numeracy","score":0.29409998655319214},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.24269999563694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5866000056266785},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4684999883174896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.420199990272522},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3824999928474426},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3781999945640564},{"id":"https://openalex.org/C53537400","wikidata":"https://www.wikidata.org/wiki/Q140637","display_name":"Numeracy","level":3,"score":0.29409998655319214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24860000610351562},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.24480000138282776},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.24269999563694},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.24079999327659607}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.289","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.289","pdf_url":"https://aclanthology.org/2026.findings-eacl.289.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.289","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.289","pdf_url":"https://aclanthology.org/2026.findings-eacl.289.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":"Findings of the Association for Computational Linguistics: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8429511189460754,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140113680.pdf","grobid_xml":"https://content.openalex.org/works/W7140113680.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text":[0],"embedding":[1,35,51,101,119,138,146],"models":[2,36,52,102,120],"are":[3,53],"widely":[4,116],"used":[5,117],"in":[6,26,56,92,109],"natural":[7],"language":[8],"processing":[9],"applications.However,":[10],"their":[11],"capability":[12],"is":[13,48],"often":[14],"benchmarked":[15],"on":[16],"tasks":[17],"that":[18,123],"do":[19],"not":[20],"require":[21],"understanding":[22],"nuanced":[23],"numerical":[24,40,129,155],"information":[25],"text.As":[27],"a":[28,110],"result,":[29],"it":[30],"remains":[31],"unclear":[32],"whether":[33,99],"current":[34],"can":[37,103],"precisely":[38],"encode":[39],"content,":[41],"such":[42,61,105],"as":[43,62],"numbers,":[44],"into":[45,137],"embeddings.This":[46],"question":[47],"critical":[49],"because":[50],"increasingly":[54],"applied":[55],"domains":[57],"where":[58],"numbers":[59],"matter,":[60],"finance":[63],"and":[64,121],"healthcare.For":[65],"example,":[66],"\"Company":[67,80],"X's":[68,81],"market":[69,82,93],"share":[70,83],"grew":[71,84],"by":[72,85],"2%\"":[73],"should":[74],"be":[75],"interpreted":[76],"very":[77],"differently":[78],"from":[79],"20%,\"":[86],"even":[87],"though":[88],"both":[89],"indicate":[90],"growth":[91],"share.This":[94],"study":[95],"aims":[96],"to":[97,127,143],"examine":[98],"text":[100,118],"capture":[104,128],"nuances.Using":[106],"synthetic":[107],"data":[108],"financial":[111],"context,":[112],"we":[113],"evaluate":[114],"13":[115],"find":[122],"they":[124],"generally":[125],"struggle":[126],"details":[130],"accurately.Our":[131],"further":[132],"analyses":[133],"provide":[134],"deeper":[135],"insights":[136],"numeracy,":[139],"informing":[140],"future":[141],"research":[142],"strengthen":[144],"the":[145],"modelbased":[147],"NLP":[148],"systems":[149],"with":[150],"improved":[151],"capacity":[152],"for":[153],"handling":[154],"content.":[156]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}