{"id":"https://openalex.org/W4416033904","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1086","title":"Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","display_name":"Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416033904","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1086"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1086","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1086","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1086.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.1086.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078160632","display_name":"Paramita Mirza","orcid":null},"institutions":[{"id":"https://openalex.org/I78650965","display_name":"Technische Universit\u00e4t Dresden","ror":"https://ror.org/042aqky30","country_code":"DE","type":"education","lineage":["https://openalex.org/I78650965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Paramita Mirza","raw_affiliation_strings":["ScaDS.AI & TU Dresden , Germany ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ScaDS.AI & TU Dresden , Germany ,","institution_ids":["https://openalex.org/I78650965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108638942","display_name":"Lucas Weber","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095661","display_name":"Fraunhofer Institute for Integrated Circuits IIS, Division Engineering of Adaptive Systems EAS","ror":"https://ror.org/00s5yp124","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210095661","https://openalex.org/I4210124274","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lucas Weber","raw_affiliation_strings":["Fraunhofer IIS , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS , Germany","institution_ids":["https://openalex.org/I4210095661","https://openalex.org/I4210124274"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120024557","display_name":"Fabian K\u00fcch","orcid":null},"institutions":[{"id":"https://openalex.org/I4210095661","display_name":"Fraunhofer Institute for Integrated Circuits IIS, Division Engineering of Adaptive Systems EAS","ror":"https://ror.org/00s5yp124","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210095661","https://openalex.org/I4210124274","https://openalex.org/I4923324"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Fabian K\u00fcch","raw_affiliation_strings":["Fraunhofer IIS , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer IIS , Germany","institution_ids":["https://openalex.org/I4210095661","https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.37598358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19949","last_page":"19974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10826","display_name":"Behavioral and Psychological Studies","score":0.20960000157356262,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10826","display_name":"Behavioral and Psychological Studies","score":0.20960000157356262,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.11169999837875366,"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/T11526","display_name":"Innovative Teaching Methods","score":0.0364999994635582,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.48429998755455017},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3107999861240387},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.30480000376701355},{"id":"https://openalex.org/keywords/control-system","display_name":"Control system","score":0.29989999532699585},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2915000021457672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6349999904632568},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.48429998755455017},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38429999351501465},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.296099990606308},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2915000021457672},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29109999537467957},{"id":"https://openalex.org/C49898467","wikidata":"https://www.wikidata.org/wiki/Q1517706","display_name":"Stratified sampling","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1086","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1086","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1086.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"},{"id":"pmh:oai:publica.fraunhofer.de:publica/512368","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/512368","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"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":"conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1086","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1086","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1086.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":[{"id":"https://openalex.org/F4320336851","display_name":"Zentrum f\u00fcr Informationsdienste und Hochleistungsrechnen, Technische Universit\u00e4t Dresden","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416033904.pdf","grobid_xml":"https://content.openalex.org/works/W4416033904.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"work":[1,88],"shows":[2],"that":[3,33],"post-training":[4],"datasets":[5],"for":[6,78],"LLMs":[7],"can":[8,36],"be":[9,37],"substantially":[10],"downsampled":[11],"without":[12],"noticeably":[13],"deteriorating":[14],"performance.However,":[15],"data":[16,34,50],"selection":[17,35],"often":[18],"incurs":[19],"high":[20],"computational":[21],"costs":[22],"or":[23],"is":[24],"limited":[25],"to":[26,70],"narrow":[27],"domains.In":[28],"this":[29],"paper,":[30],"we":[31,47,84],"demonstrate":[32],"both-efficient":[38],"and":[39,59,92],"universal-by":[40],"using":[41,56,89],"a":[42,63,93],"multi-step":[43],"pipeline":[44],"in":[45],"which":[46],"efficiently":[48],"bin":[49],"points":[51],"into":[52],"groups,":[53],"estimate":[54],"quality":[55],"specialized":[57],"models,":[58],"score":[60],"difficulty":[61],"with":[62,101],"robust,":[64],"lightweight":[65],"method.Task-based":[66],"categorization":[67],"allows":[68],"us":[69],"control":[71],"the":[72],"composition":[73],"of":[74],"our":[75],"final":[76],"data-crucial":[77],"finetuning":[79],"multi-purpose":[80],"models.To":[81],"guarantee":[82],"diversity,":[83],"improve":[85],"upon":[86],"previous":[87],"embedding":[90],"models":[91],"clustering":[94],"algorithm.This":[95],"integrated":[96],"strategy":[97],"enables":[98],"high-performance":[99],"fine-tuning":[100],"minimal":[102],"overhead.":[103]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-11-08T00:00:00"}