{"id":"https://openalex.org/W4412888402","doi":"https://doi.org/10.18653/v1/2025.findings-acl.380","title":"Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation","display_name":"Self-Foveate: Enhancing Diversity and Difficulty of Synthesized Instructions from Unsupervised Text via Multi-Level Foveation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888402","doi":"https://doi.org/10.18653/v1/2025.findings-acl.380"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.380","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.380","pdf_url":"https://aclanthology.org/2025.findings-acl.380.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.380.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100775679","display_name":"Mingzhe Li","orcid":"https://orcid.org/0000-0002-6990-0723"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingzhe Li","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics Harbin Institute of Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics Harbin Institute of Technology , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091489017","display_name":"Xinzheng Lu","orcid":"https://orcid.org/0000-0002-3313-7420"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Lu","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics Harbin Institute of Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics Harbin Institute of Technology , China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040196605","display_name":"Yanyan Zhao","orcid":"https://orcid.org/0000-0002-1166-1459"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyan Zhao","raw_affiliation_strings":["Research Center for Social Computing and Interactive Robotics Harbin Institute of Technology , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Center for Social Computing and Interactive Robotics Harbin Institute of Technology , China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"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":"7274","last_page":"7289"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8959000110626221,"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":0.8959000110626221,"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/computer-science","display_name":"Computer science","score":0.6494255661964417},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.6265279650688171},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4070318341255188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3323013186454773},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.06871351599693298}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6494255661964417},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.6265279650688171},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4070318341255188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3323013186454773},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.06871351599693298},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.380","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.380","pdf_url":"https://aclanthology.org/2025.findings-acl.380.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"},{"id":"pmh:doi:10.48550/arxiv.2507.23440","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.380","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.380","pdf_url":"https://aclanthology.org/2025.findings-acl.380.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":[],"awards":[{"id":"https://openalex.org/G2656429412","display_name":null,"funder_award_id":"62176078","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888402.pdf","grobid_xml":"https://content.openalex.org/works/W4412888402.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4281758439"],"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/W3204019825"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"with":[4],"instruction":[5,71],"following":[6],"capabilities":[7],"have":[8,42],"demonstrated":[9],"impressive":[10],"problem-solving":[11],"abilities.While":[12],"synthesizing":[13],"instructional":[14],"data":[15,36,125],"from":[16],"unsupervised":[17,92,107],"text":[18],"has":[19],"become":[20],"a":[21,75],"common":[22],"approach":[23,73],"for":[24,35,70],"training":[25],"such":[26],"models,":[27],"conventional":[28],"methods":[29],"rely":[30],"heavily":[31],"on":[32],"human":[33],"effort":[34],"annotation.Although":[37],"existing":[38],"automated":[39],"synthesis":[40],"paradigms":[41],"alleviated":[43],"this":[44],"constraint,":[45],"they":[46],"still":[47],"exhibit":[48],"significant":[49],"limitations":[50],"in":[51,91],"ensuring":[52],"adequate":[53],"diversity":[54,98],"and":[55,99,109,116,126],"difficulty":[56,100],"of":[57,101,118],"synthesized":[58,102],"instructions.To":[59],"address":[60],"these":[61],"challenges,":[62],"we":[63],"propose":[64],"SELF-FOVEATE,":[65],"an":[66],"innovative":[67],"LLMdriven":[68],"method":[69],"synthesis.This":[72],"introduces":[74],"\"Micro-Scatter-Macro\"":[76],"multi-level":[77],"foveation":[78],"methodology":[79],"that":[80],"effectively":[81],"guides":[82],"the":[83,97,114],"LLM":[84],"to":[85],"deeply":[86],"excavate":[87],"finegrained":[88],"information":[89],"embedded":[90],"text,":[93],"thereby":[94],"enhancing":[95],"both":[96],"instructions.Comprehensive":[103],"experiments":[104],"across":[105],"multiple":[106],"corpora":[108],"diverse":[110],"model":[111],"architectures":[112],"validate":[113],"effectiveness":[115],"superiority":[117],"our":[119,124],"proposed":[120],"method.We":[121],"publicly":[122],"release":[123],"codes:":[127],"https://github.com/Mubuky/Self-Foveate":[128]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}