{"id":"https://openalex.org/W7140103265","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.79","title":"CrowdSelect: SyntheticInstruction Data Selection with Multi-LLM Wisdom","display_name":"CrowdSelect: SyntheticInstruction Data Selection with Multi-LLM Wisdom","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140103265","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.79"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.79","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.79","pdf_url":"https://aclanthology.org/2026.findings-eacl.79.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: EACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-eacl.79.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130404704","display_name":"Yisen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yisen Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130348342","display_name":"Lingfeng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingfeng Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130401713","display_name":"Wenxuan Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenxuan Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130372327","display_name":"Pan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102201025","display_name":"Yao Wan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130332215","display_name":"Weiwei Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Weiwei Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130365756","display_name":"Dongping Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongping Chen","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":"1542","last_page":"1569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.8531000018119812,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.8531000018119812,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.010300000198185444,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.007199999876320362,"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/selection","display_name":"Selection (genetic algorithm)","score":0.4074000120162964},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.30059999227523804},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2605000138282776},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.25209999084472656},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.23909999430179596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.555899977684021},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47200000286102295},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4074000120162964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31779998540878296},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24639999866485596},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.23909999430179596},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.2313999980688095}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.79","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.79","pdf_url":"https://aclanthology.org/2026.findings-eacl.79.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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.79","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.79","pdf_url":"https://aclanthology.org/2026.findings-eacl.79.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G664739573","display_name":null,"funder_award_id":"62476107","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140103265.pdf","grobid_xml":"https://content.openalex.org/works/W7140103265.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Distilling":[0],"advanced":[1],"Large":[2],"Language":[3],"Models'":[4],"instruction-following":[5],"capabilities":[6],"into":[7],"smaller":[8],"models":[9,110],"using":[10],"a":[11,16,90],"selected":[12],"subset":[13],"has":[14],"become":[15],"mainstream":[17],"approach":[18,92],"in":[19,122,150],"model":[20,36,78],"training.While":[21],"existing":[22],"synthetic":[23],"instruction":[24],"data":[25],"selection":[26],"strategies":[27],"rely":[28],"mainly":[29],"on":[30,111,132,136],"single-dimensional":[31],"signals":[32,53],"(i.e.,":[33],"reward":[34,77],"scores,":[35],"perplexity),":[37],"they":[38],"fail":[39],"to":[40,54,93],"capture":[41,55],"the":[42],"complexity":[43],"of":[44,130],"instructionfollowing":[45],"across":[46,107],"diverse":[47,52,72],"fields.Therefore,":[48],"we":[49,83],"investigate":[50],"more":[51],"comprehensive":[56,97],"instruction-response":[57],"pair":[58],"characteristics":[59],"and":[60,75,113,125,134],"propose":[61,84],"three":[62],"foundational":[63],"metrics":[64,103],"that":[65,100],"leverage":[66],"Multi-LLM":[67],"wisdom,":[68],"informed":[69],"by":[70],"(1)":[71],"LLM":[73],"responses":[74],"(2)":[76],"assessment.Building":[79],"upon":[80],"base":[81,109],"metrics,":[82,118],"CROWDSELECT,":[85],"an":[86],"integrated":[87],"metric":[88],"incorporating":[89,116],"clustering-based":[91],"maintain":[94],"response":[95],"diversity.Our":[96],"experiments":[98],"demonstrate":[99],"our":[101,141],"foundation":[102],"consistently":[104],"improve":[105],"performance":[106,121],"4":[108],"MT-bench":[112,137],"Arena-Hard.CROWD-SELECT,":[114],"efficiently":[115],"all":[117],"achieves":[119],"state-of-the-art":[120],"both":[123],"Full":[124],"LoRA":[126],"fine-tuning,":[127],"showing":[128],"improvements":[129],"4.81%":[131],"Arena-Hard":[133],"11.1%":[135],"with":[138],"Llama-3.2-3b-instruct.We":[139],"hope":[140],"findings":[142],"will":[143],"bring":[144],"valuable":[145],"insights":[146],"for":[147],"future":[148],"research":[149],"this":[151],"direction.":[152]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-24T00:00:00"}