{"id":"https://openalex.org/W4412888931","doi":"https://doi.org/10.18653/v1/2025.findings-acl.51","title":"ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Study","display_name":"ORBIT: Cost-Effective Dataset Curation for Large Language Model Domain Adaptation with an Astronomy Case Study","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888931","doi":"https://doi.org/10.18653/v1/2025.findings-acl.51"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.51","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.51","pdf_url":"https://aclanthology.org/2025.findings-acl.51.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: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.51.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115561087","display_name":"Eric Modesitt","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Modesitt","raw_affiliation_strings":["University of Illinois at Urbana-Champaign National Center for Supercomputing Applications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign National Center for Supercomputing Applications","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115597573","display_name":"Ke Yang","orcid":"https://orcid.org/0009-0009-2159-4980"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ke Yang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign National Center for Supercomputing Applications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign National Center for Supercomputing Applications","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115561088","display_name":"Spencer Hulsey","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Spencer Hulsey","raw_affiliation_strings":["University of Illinois at Urbana-Champaign National Center for Supercomputing Applications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign National Center for Supercomputing Applications","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108648432","display_name":"ChengXiang Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"ChengXiang Zhai","raw_affiliation_strings":["University of Illinois at Urbana-Champaign National Center for Supercomputing Applications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign National Center for Supercomputing Applications","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060025664","display_name":"Volodymyr Kindratenko","orcid":"https://orcid.org/0000-0002-9336-4756"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Volodymyr Kindratenko","raw_affiliation_strings":["University of Illinois at Urbana-Champaign National Center for Supercomputing Applications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign National Center for Supercomputing Applications","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"907","last_page":"926"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.989799976348877,"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/T10028","display_name":"Topic Modeling","score":0.989799976348877,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9811000227928162,"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/adaptation","display_name":"Adaptation (eye)","score":0.6929374933242798},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6894736289978027},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5264490246772766},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5106757283210754},{"id":"https://openalex.org/keywords/orbit","display_name":"Orbit (dynamics)","score":0.4888159930706024},{"id":"https://openalex.org/keywords/astronomy","display_name":"Astronomy","score":0.4607800543308258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21702897548675537},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13452968001365662},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11083227396011353},{"id":"https://openalex.org/keywords/aerospace-engineering","display_name":"Aerospace engineering","score":0.10227322578430176}],"concepts":[{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.6929374933242798},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6894736289978027},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5264490246772766},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5106757283210754},{"id":"https://openalex.org/C196644772","wikidata":"https://www.wikidata.org/wiki/Q3884964","display_name":"Orbit (dynamics)","level":2,"score":0.4888159930706024},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.4607800543308258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21702897548675537},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13452968001365662},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11083227396011353},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.10227322578430176},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.51","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.51","pdf_url":"https://aclanthology.org/2025.findings-acl.51.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: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.51","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.51","pdf_url":"https://aclanthology.org/2025.findings-acl.51.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: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G130758723","display_name":"AI Institute for Inclusive Intelligent Technologies for Education (INVITE)","funder_award_id":"2229612","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1912064254","display_name":"Track 4:  Advanced CI Coordination Ecosystem: Monitoring and Measurement Services","funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2507572247","display_name":null,"funder_award_id":"2138286","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G4006316252","display_name":"Track 1: ACCESS Resource Allocations Marketplace and Platform Services (RAMPS)","funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4010157413","display_name":null,"funder_award_id":"2138259","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G509285653","display_name":"Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT)","funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5464919783","display_name":null,"funder_award_id":"2137603","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G5942125552","display_name":null,"funder_award_id":"2229612","funder_id":"https://openalex.org/F4320332210","funder_display_name":"Institute of Education Sciences"},{"id":"https://openalex.org/G6664589177","display_name":null,"funder_award_id":"2138307","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"},{"id":"https://openalex.org/G7862828139","display_name":null,"funder_award_id":"DRL-2229612","funder_id":"https://openalex.org/F4320332210","funder_display_name":"Institute of Education Sciences"},{"id":"https://openalex.org/G8300691027","display_name":"Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI","funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8897435675","display_name":null,"funder_award_id":"2138296","funder_id":"https://openalex.org/F4320337377","funder_display_name":"Office of Advanced Cyberinfrastructure"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332210","display_name":"Institute of Education Sciences","ror":"https://ror.org/04et59085"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888931.pdf","grobid_xml":"https://content.openalex.org/works/W4412888931.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4394775207","https://openalex.org/W4389474468","https://openalex.org/W4300172004","https://openalex.org/W3203792196","https://openalex.org/W4321649381","https://openalex.org/W2997645659","https://openalex.org/W3180787869","https://openalex.org/W4295929828","https://openalex.org/W3156096827"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,129],"language":[3,71],"modeling":[4],"demonstrate":[5],"the":[6,25,81,102,161,165,168,171],"need":[7],"for":[8,14,28,56,67],"high-quality":[9,46,59],"domain-specific":[10,34,60],"training":[11,37,68],"data,":[12],"especially":[13],"tasks":[15,30],"that":[16],"require":[17],"specialized":[18],"knowledge.General-purpose":[19],"models,":[20,41],"while":[21],"versatile,":[22],"often":[23],"lack":[24],"depth":[26],"needed":[27],"expert-level":[29],"because":[31],"of":[32,131,152],"limited":[33],"information.Domain":[35],"adaptation":[36],"can":[38],"enhance":[39],"these":[40],"but":[42],"it":[43,128,143],"demands":[44],"substantial,":[45],"data.To":[47],"address":[48],"this,":[49],"we":[50,79,137],"propose":[51],"ORBIT,":[52],"a":[53,75,86,95,149],"costefficient":[54],"methodology":[55],"curating":[57],"massive,":[58],"datasets":[61],"from":[62,106],"noisy":[63],"web":[64],"sources,":[65],"tailored":[66],"specialist":[69],"large":[70],"models.Using":[72],"astronomy":[73,97,104],"as":[74],"primary":[76],"case":[77],"study,":[78],"refined":[80],"1.3T-token":[82],"FineWeb-Edu":[83],"dataset":[84],"into":[85],"highquality,":[87],"10B-token":[88],"subset":[89,98],"focused":[90],"on":[91,94,101,114],"astronomy.Fine-tuning":[92],"LLAMA-3-8B":[93],"1Btoken":[96],"improved":[99],"performance":[100],"MMLU":[103],"benchmark":[105],"69%":[107],"to":[108,144,156],"76%":[109],"and":[110,146,170],"achieved":[111],"top":[112],"results":[113],"As-troBench,":[115],"an":[116,157],"astronomy-specific":[117,135],"benchmark.Moreover,":[118],"our":[119],"model":[120,173],"(Orbit-LLaMA)":[121],"outperformed":[122],"LLAMA-3-8B-BASE,":[123],"with":[124],"GPT-4o":[125],"evaluations":[126],"preferring":[127],"73%":[130],"cases":[132],"across":[133],"1000":[134],"questions.Additionally,":[136],"validated":[138],"ORBIT's":[139],"generalizability":[140],"by":[141],"applying":[142],"law":[145],"medicine,":[147],"achieving":[148],"significant":[150],"improvement":[151],"data":[153],"quality":[154],"compared":[155],"unfiltered":[158],"baseline.We":[159],"open-source":[160],"ORBIT":[162],"methodology,":[163],"including":[164],"curated":[166],"datasets,":[167],"codebase,":[169],"resulting":[172],"at":[174],"https://github.com/ModeEric/ORBIT-Llama.":[175]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}