{"id":"https://openalex.org/W4416034833","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.437","title":"Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning","display_name":"Low-Confidence Gold: Refining Low-Confidence Samples for Efficient Instruction Tuning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034833","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.437"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.437","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.437","pdf_url":"https://aclanthology.org/2025.findings-emnlp.437.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: EMNLP 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-emnlp.437.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101029619","display_name":"Hongyi Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyi Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100428230","display_name":"Jie Li","orcid":"https://orcid.org/0000-0002-3272-4850"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110190317","display_name":"M M Rahman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Mahdinur Rahman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102702009","display_name":"Wenzhen Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenzhen Dong","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8233","last_page":"8240"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.09040000289678574,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.09040000289678574,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0658000037074089,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.027300000190734863,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/refining","display_name":"Refining (metallurgy)","score":0.484499990940094},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.38519999384880066},{"id":"https://openalex.org/keywords/process-control","display_name":"Process control","score":0.3294999897480011},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.30480000376701355},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3034000098705292},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2766000032424927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5611000061035156},{"id":"https://openalex.org/C60044698","wikidata":"https://www.wikidata.org/wiki/Q1283324","display_name":"Refining (metallurgy)","level":2,"score":0.484499990940094},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.38519999384880066},{"id":"https://openalex.org/C155386361","wikidata":"https://www.wikidata.org/wiki/Q1649571","display_name":"Process control","level":3,"score":0.3294999897480011},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2538999915122986},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2508000135421753},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.437","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.437","pdf_url":"https://aclanthology.org/2025.findings-emnlp.437.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.437","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.437","pdf_url":"https://aclanthology.org/2025.findings-emnlp.437.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034833.pdf","grobid_xml":"https://content.openalex.org/works/W4416034833.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"effectiveness":[1],"of":[2,17,68],"instruction":[3,39,102],"fine-tuning":[4],"for":[5,36,100],"Large":[6],"Language":[7],"Models":[8],"is":[9],"fundamentally":[10],"constrained":[11],"by":[12],"the":[13],"quality":[14],"and":[15,33,83],"efficiency":[16],"training":[18],"datasets.This":[19],"work":[20],"introduces":[21],"Low-Confidence":[22],"Gold":[23],"(LCG),":[24],"a":[25,41,45,97],"novel":[26],"filtering":[27],"framework":[28],"that":[29,62],"employs":[30],"centroid-based":[31],"clustering":[32],"confidence-guided":[34],"selection":[35],"identifying":[37],"valuable":[38],"pairs.Through":[40],"semi-supervised":[42],"approach":[43],"using":[44],"lightweight":[46],"classifier":[47],"trained":[48],"on":[49,65,81],"representative":[50],"samples,":[51],"LCG":[52],"curates":[53],"high-quality":[54],"subsets":[55,67],"while":[56,92],"preserving":[57],"data":[58],"diversity.Experimental":[59],"evaluation":[60,88],"demonstrates":[61],"models":[63],"fine-tuned":[64],"LCGfiltered":[66],"6K":[69],"samples":[70],"achieve":[71],"superior":[72],"performance":[73,95],"compared":[74],"to":[75],"existing":[76],"methods,":[77],"with":[78],"substantial":[79],"improvements":[80],"MT-bench":[82],"consistent":[84],"gains":[85],"across":[86],"comprehensive":[87],"metrics.The":[89],"framework's":[90],"efficacy":[91],"maintaining":[93],"model":[94],"establishes":[96],"promising":[98],"result":[99],"efficient":[101],"tuning.":[103]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}