{"id":"https://openalex.org/W4414742277","doi":"https://doi.org/10.18653/v1/2026.acl-long.1799","title":"BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes","display_name":"BEFT: Bias-Efficient Fine-Tuning of Language Models in Low-Data Regimes","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414742277","doi":"https://doi.org/10.18653/v1/2026.acl-long.1799"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1799","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1799","pdf_url":"https://aclanthology.org/2026.acl-long.1799.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1799.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031296968","display_name":"Baichuan Huang","orcid":"https://orcid.org/0000-0002-9658-6071"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baichuan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119810946","display_name":"Ananth Balashankar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ananth Balashankar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5024972825","display_name":"Amir Aminifar","orcid":"https://orcid.org/0000-0002-1673-4733"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amir Aminifar","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":0.007554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"38833","last_page":"38851"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9905999898910522,"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":0.9905999898910522,"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/T10028","display_name":"Topic Modeling","score":0.9894000291824341,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9692000150680542,"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/language-model","display_name":"Language model","score":0.5680000185966492},{"id":"https://openalex.org/keywords/usability","display_name":"Usability","score":0.5541999936103821},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4717999994754791},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.46230000257492065},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.3634999990463257},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.3237999975681305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044000029563904},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5680000185966492},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.5541999936103821},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.46230000257492065},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.424699991941452},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3630000054836273},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3228999972343445},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2662000060081482}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1799","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1799","pdf_url":"https://aclanthology.org/2026.acl-long.1799.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.15974","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.15974","pdf_url":"https://arxiv.org/pdf/2509.15974","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"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":"text"},{"id":"pmh:oai:arXiv.org:2509.15974","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.15974","pdf_url":"https://arxiv.org/pdf/2509.15974","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.15974","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.15974","pdf_url":null,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1799","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1799","pdf_url":"https://aclanthology.org/2026.acl-long.1799.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320940","display_name":"Stiftelsen f\u00f6r\u00a0Strategisk Forskning","ror":"https://ror.org/044wr7g58"},{"id":"https://openalex.org/F4320322581","display_name":"Vetenskapsr\u00e5det","ror":"https://ror.org/03zttf063"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414742277.pdf","grobid_xml":"https://content.openalex.org/works/W4414742277.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"the":[1,10,25,43,61,75,78,135],"bias":[2,30],"terms":[3,31],"of":[4,77,116,137],"large":[5],"language":[6],"models":[7],"(LLMs)":[8],"has":[9],"potential":[11],"to":[12,55,91,100,124],"achieve":[13],"unprecedented":[14],"parameter":[15],"efficiency":[16],"while":[17],"maintaining":[18],"competitive":[19],"performance,":[20],"particularly":[21],"in":[22,42,95,98],"low-data":[23,96],"regimes.However,":[24],"link":[26,62],"between":[27,63],"fine-tuning":[28,64,86,139],"different":[29],"(i.e.,":[32],"b":[33,36,40,65,68,72,87,101,104,140],"q":[34,66,102],",":[35,38,67,70],"k":[37,69,105],"and":[39,49,71,103,120],"v":[41,73,88,141],"query,":[44],"key,":[45],"or":[46],"value":[47],"projections)":[48],"downstream":[50,79,93,144],"performance":[51,76,94],"remains":[52],"largely":[53],"unclear":[54],"date.In":[56],"this":[57,109],"paper,":[58],"we":[59],"investigate":[60],"with":[74],"task.Our":[80],"key":[81],"finding":[82],"is":[83,148],"that":[84],"directly":[85,138],"generally":[89],"leads":[90],"higher":[92],"regimes,":[97],"comparison":[99],".We":[106],"extensively":[107],"evaluate":[108],"unique":[110],"property":[111],"across":[112,142],"a":[113],"wide":[114],"range":[115],"LLMs":[117],"spanning":[118],"encoder-only":[119],"decoderonly":[121],"architectures":[122],"up":[123],"6.7B":[125],"parameters":[126],"(including":[127],"bias-free":[128],"LLMs).Our":[129],"results":[130],"provide":[131],"strong":[132],"evidence":[133],"for":[134],"effectiveness":[136],"various":[143],"tasks.The":[145],"implementation":[146],"code":[147],"available":[149],"at":[150],"https:":[151],"//github.com/whubaichuan/BEFT.":[152]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}