{"id":"https://openalex.org/W4413925411","doi":"https://doi.org/10.1109/access.2025.3605290","title":"Entropy-Based Data Selection for Language Models","display_name":"Entropy-Based Data Selection for Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4413925411","doi":"https://doi.org/10.1109/access.2025.3605290"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3605290","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3605290","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3605290","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Hongming Li","orcid":"https://orcid.org/0009-0004-2042-8896"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongming Li","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","School of Computer and Communication Engineering, University of Science and Technology Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-2042-8896","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100356161","display_name":"Yang Liu","orcid":"https://orcid.org/0000-0003-3800-3533"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4392738278","display_name":"Beijing Institute for General Artificial Intelligence","ror":"https://ror.org/02kw1ws04","country_code":"CN","type":"government","lineage":["https://openalex.org/I4392738278"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["National Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence, Beijing, China","National Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]},{"raw_affiliation_string":"National Key Laboratory of General Artificial Intelligence, Beijing Institute for General Artificial Intelligence, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4392738278"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070357433","display_name":"Chao Huang","orcid":"https://orcid.org/0000-0002-8012-3697"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Huang","raw_affiliation_strings":["School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","School of Computer and Communication Engineering, University of Science and Technology Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8012-3697","affiliations":[{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"School of Computer and Communication Engineering, University of Science and Technology Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":2.1733,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.90228369,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"13","issue":null,"first_page":"153713","last_page":"153727"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8682000041007996,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.8682000041007996,"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/computer-science","display_name":"Computer science","score":0.7191856503486633},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.502260684967041},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4737575650215149},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4635789692401886},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.43984416127204895},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4274749159812927},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37994149327278137},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11314666271209717}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7191856503486633},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.502260684967041},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4737575650215149},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4635789692401886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43984416127204895},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4274749159812927},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37994149327278137},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11314666271209717},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2025.3605290","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3605290","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:doi:10.48550/arxiv.2602.17465","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:a024ccb2c43e4fd98a054a71c12f3dfb","is_oa":true,"landing_page_url":"https://doaj.org/article/a024ccb2c43e4fd98a054a71c12f3dfb","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 153713-153727 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3605290","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3605290","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3690819622","display_name":null,"funder_award_id":"62002016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4848897788","display_name":null,"funder_award_id":"62372039","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8468067264","display_name":null,"funder_award_id":"2022A1515240044","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1493526108","https://openalex.org/W1971656131","https://openalex.org/W3084095723","https://openalex.org/W4385819657","https://openalex.org/W4387683626","https://openalex.org/W4391132294","https://openalex.org/W4398788555","https://openalex.org/W4399803256","https://openalex.org/W4401042766","https://openalex.org/W4404518211","https://openalex.org/W4405483221","https://openalex.org/W4406679848","https://openalex.org/W4410949639"],"related_works":["https://openalex.org/W4205762803","https://openalex.org/W2535856026","https://openalex.org/W2265065644","https://openalex.org/W2134699697","https://openalex.org/W3017188156","https://openalex.org/W2322875716","https://openalex.org/W2383516975","https://openalex.org/W2374878784","https://openalex.org/W2147679489","https://openalex.org/W2371642785"],"abstract_inverted_index":{"Modern":[0],"language":[1,70,77],"models":[2,71],"(LMs)":[3],"increasingly":[4],"require":[5,40],"two":[6],"critical":[7],"resources:":[8],"computational":[9,36,154],"resources":[10],"and":[11,62,79,125,142,156],"data":[12,24,60,87,90,99,163],"resources.":[13],"Data":[14,112],"selection":[15,61,100],"techniques":[16],"can":[17],"effectively":[18],"reduce":[19],"the":[20,47,57,146,171,177],"amount":[21],"of":[22,65,148,174],"training":[23,158],"required":[25],"for":[26,170],"fine-tuning":[27,52,173],"LMs.":[28],"However,":[29],"their":[30],"effectiveness":[31,147],"is":[32],"closely":[33],"related":[34],"to":[35,46,85],"resources,":[37],"which":[38,81],"always":[39],"a":[41,93,135],"high":[42],"compute":[43],"budget.":[44],"Owing":[45],"resource":[48],"limitations":[49],"in":[50,76,176],"practical":[51],"scenario,":[53],"we":[54,106],"systematically":[55],"reveal":[56],"relationship":[58],"between":[59],"uncertainty":[63],"estimation":[64],"selected":[66],"data.":[67],"Although":[68],"large":[69],"(LLMs)":[72],"exhibit":[73],"exceptional":[74],"capabilities":[75],"understanding":[78],"generation,":[80],"provide":[82],"new":[83],"ways":[84],"alleviate":[86],"scarcity,":[88],"evaluating":[89],"usability":[91],"remains":[92],"challenging":[94],"task.":[95],"This":[96,165],"makes":[97],"efficient":[98,137,172],"indispensable.":[101],"To":[102],"mitigate":[103],"these":[104],"issues,":[105],"propose":[107],"<italic":[108],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[109],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Entropy-Based":[110],"Unsupervised":[111],"Selection":[113],"(EUDS)</i>":[114],"framework.":[115],"Empirical":[116],"experiments":[117],"on":[118],"sentiment":[119],"analysis":[120,141],"(SA),":[121],"topic":[122],"classification":[123],"(Topic-CLS),":[124],"question":[126],"answering":[127],"(Q&A)":[128],"tasks":[129],"validate":[130],"its":[131],"effectiveness.":[132],"EUDS":[133,151],"establishes":[134],"computationally":[136],"data-filtering":[138],"mechanism.":[139],"Theoretical":[140],"experimental":[143],"results":[144],"confirm":[145],"our":[149],"approach.":[150],"significantly":[152],"reduces":[153],"costs":[155],"improves":[157],"time":[159],"efficiency":[160],"with":[161],"less":[162],"requirement.":[164],"provides":[166],"an":[167],"innovative":[168],"solution":[169],"LMs":[175],"compute-constrained":[178],"scenarios.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}