{"id":"https://openalex.org/W7161985361","doi":"https://doi.org/10.48550/arxiv.2605.20924","title":"Strategy-Induct: Task-Level Strategy Induction for Instruction Generation","display_name":"Strategy-Induct: Task-Level Strategy Induction for Instruction Generation","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7161985361","doi":"https://doi.org/10.48550/arxiv.2605.20924"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20924","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.20924","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136635375","display_name":"Po-Chun Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Po-Chun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136718209","display_name":"Hen-Hsen Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Hen-Hsen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136690975","display_name":"Hsin-Hsi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hsin-Hsi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5314000248908997,"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/T10028","display_name":"Topic Modeling","score":0.5314000248908997,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15929999947547913,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.07530000060796738,"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/task","display_name":"Task (project management)","score":0.7555999755859375},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6449000239372253},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.541100025177002},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.38850000500679016},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.349700003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7734000086784363},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7555999755859375},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6449000239372253},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.541100025177002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45820000767707825},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.38850000500679016},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.349700003862381},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3319000005722046},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31450000405311584},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30309998989105225},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20924","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.20924","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20924","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.4046010375022888,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Designing":[0],"effective":[1],"task-level":[2,58],"prompts":[3,75],"is":[4],"crucial":[5],"for":[6,83],"improving":[7],"the":[8,76],"performance":[9,140],"of":[10,65],"Large":[11,127],"Language":[12],"Models":[13,129],"(LLMs).":[14],"While":[15],"prior":[16],"work":[17],"on":[18,35],"instruction":[19,99,132],"induction":[20],"demonstrates":[21],"that":[22,56,100,111,122],"LLMs":[23,125],"can":[24,42],"infer":[25],"better":[26],"instructions":[27,59],"with":[28],"limited":[29],"examples,":[30],"existing":[31],"approaches":[32],"often":[33],"rely":[34],"input-output":[36],"pairs,":[37],"where":[38],"obtaining":[39],"labeled":[40,70],"answers":[41],"be":[43],"difficult":[44],"or":[45],"costly.":[46],"To":[47],"address":[48],"this":[49],"limitation,":[50],"we":[51,120],"propose":[52],"Strategy-Induct,":[53],"a":[54,62,97],"framework":[55],"derives":[57],"solely":[60],"from":[61],"small":[63],"set":[64],"example":[66],"questions":[67],"without":[68],"requiring":[69],"answers.":[71],"Our":[72],"approach":[73],"first":[74],"model":[77,108],"to":[78,95,138],"generate":[79],"explicit":[80],"reasoning":[81],"strategies":[82],"each":[84],"question,":[85],"forming":[86],"(strategy,":[87],"question)":[88],"pairs.":[89],"These":[90],"pairs":[91],"are":[92],"then":[93],"used":[94],"induce":[96],"task":[98,131],"guides":[101],"reasoning.":[102],"Experiments":[103],"across":[104,130],"multiple":[105],"tasks":[106],"and":[107,126,134],"scales":[109],"demonstrate":[110],"Strategy-Induct":[112],"outperforms":[113],"state-of-the-art":[114],"methods":[115],"in":[116],"question-only":[117],"settings.":[118],"Furthermore,":[119],"observe":[121],"jointly":[123],"utilizing":[124],"Reasoning":[128],"generation":[133],"inference":[135],"may":[136],"lead":[137],"further":[139],"improvements.":[141]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-22T00:00:00"}