{"id":"https://openalex.org/W4412888066","doi":"https://doi.org/10.18653/v1/2025.findings-acl.906","title":"FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only","display_name":"FANNO: Augmenting High-Quality Instruction Data with Open-Sourced LLMs Only","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888066","doi":"https://doi.org/10.18653/v1/2025.findings-acl.906"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.906","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.906","pdf_url":"https://aclanthology.org/2025.findings-acl.906.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.906.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074887437","display_name":"He Zhu","orcid":"https://orcid.org/0000-0002-8732-3536"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064357587","display_name":"Yifan Ding","orcid":"https://orcid.org/0009-0009-3060-4271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yicheng Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yicheng Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiwen Ruan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiwen Ruan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068285831","display_name":"Y. Li","orcid":"https://orcid.org/0009-0001-4276-4370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixia Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100719744","display_name":"Wenjia Zhang","orcid":"https://orcid.org/0000-0002-9545-1124"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjia Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100416547","display_name":"Yun Chen","orcid":"https://orcid.org/0000-0002-4988-8894"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yun Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Guanhua Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guanhua 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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17633","last_page":"17653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9442999958992004,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9442999958992004,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/quality","display_name":"Quality (philosophy)","score":0.6209480166435242},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5087245106697083},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0989396870136261}],"concepts":[{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6209480166435242},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5087245106697083},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0989396870136261},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.906","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.906","pdf_url":"https://aclanthology.org/2025.findings-acl.906.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.906","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.906","pdf_url":"https://aclanthology.org/2025.findings-acl.906.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":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321881","display_name":"Shanghai Municipal Education Commission","ror":"https://ror.org/05tewj457"},{"id":"https://openalex.org/F4320327605","display_name":"Southern University of Science and Technology","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888066.pdf","grobid_xml":"https://content.openalex.org/works/W4412888066.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Instruction":[0],"tuning":[1],"stands":[2],"as":[3],"a":[4,97,109,153],"crucial":[5],"advancement":[6],"in":[7,93],"leveraging":[8],"large":[9],"language":[10],"models":[11],"(LLMs)":[12],"for":[13,75],"enhanced":[14],"task":[15],"performance.However,":[16],"the":[17,73,82,118,129,133,137,142],"annotation":[18,171],"of":[19,132],"instruction":[20,63,89,115,159,182],"datasets":[21],"has":[22],"traditionally":[23],"been":[24],"expensive":[25],"and":[26,68,86,90,104,108,147],"laborious,":[27],"often":[28],"relying":[29],"on":[30],"manual":[31],"annotations":[32],"or":[33,167,176],"costly":[34],"proprietary":[35,174],"LLMs.Recent":[36],"works":[37],"explore":[38],"approaches":[39],"to":[40,60,101,112,127],"synthesize":[41,61],"data":[42,64,107,116,138,150,160,183],"with":[43,65,117,152,173],"opensourced":[44,66],"LLMs":[45,67,175,178],"but":[46],"require":[47],"high-quality":[48,62,88,149],"humancrafted":[49],"seed":[50,76,106,119],"data.In":[51],"this":[52],"work,":[53],"we":[54],"introduce":[55],"FANNO,":[56],"an":[57],"end-to-end":[58],"framework":[59,83],"sampled":[69],"unlabeled":[70],"documents,":[71,81],"eliminating":[72],"necessity":[74],"data.Starting":[77],"from":[78],"diverse":[79,87,103,146],"pre-screened":[80],"synthesizes":[84],"complex":[85,105,148],"response":[91],"pairs":[92],"different":[94],"stages.We":[95],"propose":[96],"tagging-based":[98],"prompt":[99,124],"method":[100],"generate":[102,145],"UCB-based":[110],"approach":[111],"augment":[113],"more":[114],"data.A":[120],"novel":[121],"Think":[122],"Different":[123],"is":[125,164],"proposed":[126],"address":[128],"distributional":[130],"limitations":[131],"seeds,":[134],"further":[135],"boosting":[136],"diversity.Experiments":[139],"prove":[140],"that":[141,163],"FANNO":[143],"can":[144],"even":[151,168],"opensource":[154],"small":[155],"teacher":[156],"model.The":[157],"synthesized":[158],"demonstrates":[161],"performance":[162],"comparable":[165],"to,":[166],"surpasses,":[169],"baseline":[170],"methods":[172],"open-sourced":[177],"while":[179],"requiring":[180],"fewer":[181],"samples.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}