{"id":"https://openalex.org/W7147280849","doi":"https://doi.org/10.1109/cnml68938.2026.11452363","title":"Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space","display_name":"Structured Prompt Optimization for Few-Shot Text Classification via Semantic Alignment in Latent Space","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7147280849","doi":"https://doi.org/10.1109/cnml68938.2026.11452363"},"language":null,"primary_location":{"id":"doi:10.1109/cnml68938.2026.11452363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Jiasen Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jiasen Zheng","raw_affiliation_strings":["Northwestern University,Evanston,USA"],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zijun Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zijun Zhou","raw_affiliation_strings":["Independent Researcher,San Jose,USA"],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Huajun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huajun Zhang","raw_affiliation_strings":["Syracuse University,Syracuse,USA"],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Junjiang Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjiang Lin","raw_affiliation_strings":["University of Toronto,Toronto,Canada"],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jingyun Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyun Jia","raw_affiliation_strings":["University of Wisconsin-Madison,Madison,USA"],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Qi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Wang","raw_affiliation_strings":["Purdue University,West Lafayette,USA"],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.96107395,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1430","last_page":"1434"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.4844000041484833,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.4844000041484833,"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/T10028","display_name":"Topic Modeling","score":0.23819999396800995,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.08789999783039093,"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/ambiguity","display_name":"Ambiguity","score":0.5228000283241272},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.49219998717308044},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.3799999952316284},{"id":"https://openalex.org/keywords/orthogonality","display_name":"Orthogonality","score":0.37950000166893005},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3741999864578247},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.3643999993801117},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.3628999888896942},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3531000018119812},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.33550000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760999798774719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6033999919891357},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5228000283241272},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.49219998717308044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48500001430511475},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C17137986","wikidata":"https://www.wikidata.org/wiki/Q215067","display_name":"Orthogonality","level":2,"score":0.37950000166893005},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3741999864578247},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3643999993801117},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34769999980926514},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33550000190734863},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3327000141143799},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3167000114917755},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C37926939","wikidata":"https://www.wikidata.org/wiki/Q7449061","display_name":"Semantic equivalence","level":4,"score":0.28380000591278076},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.2809999883174896},{"id":"https://openalex.org/C2986420190","wikidata":"https://www.wikidata.org/wiki/Q39045939","display_name":"Semantic space","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C511149849","wikidata":"https://www.wikidata.org/wiki/Q7449051","display_name":"Semantic computing","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cnml68938.2026.11452363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cnml68938.2026.11452363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 International Conference on Communication Networks and Machine Learning (CNML)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W4302362365","https://openalex.org/W4307298796","https://openalex.org/W4308347009","https://openalex.org/W4385572887","https://openalex.org/W4385573618","https://openalex.org/W4408242356","https://openalex.org/W4414605593","https://openalex.org/W4415125240","https://openalex.org/W4416922888","https://openalex.org/W4417471170","https://openalex.org/W4417471200","https://openalex.org/W7117148199","https://openalex.org/W7131646656","https://openalex.org/W7133713463","https://openalex.org/W7134926620","https://openalex.org/W7140192390","https://openalex.org/W7140232472"],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"addresses":[2],"the":[3,48,85,91,99,125,144,147,179,184,193,226],"issues":[4],"of":[5,62,161,183],"semantic":[6,30,54,64,141,201,230],"entanglement,":[7],"unclear":[8],"label":[9,97,104,121,204],"structure,":[10],"and":[11,19,32,51,66,96,107,120,131,153,171,181,203,218,220,235,239],"insufficient":[12],"feature":[13],"representation":[14],"in":[15,84,143,206],"few-shot":[16,207,244],"text":[17,50,70,94,208,245],"classification,":[18],"proposes":[20],"an":[21,237],"optimization":[22,134,197,241],"framework":[23,39,185,198],"based":[24],"on":[25,214],"structured":[26,59,103,148,195],"prompts":[27,60,149],"to":[28,46,113,136,150,177],"enhance":[29],"understanding":[31],"task":[33],"adaptation":[34],"under":[35,186,232],"low-resource":[36],"conditions.":[37,188],"The":[38],"first":[40],"uses":[41],"a":[42,73,102,109,132],"pretrained":[43],"language":[44],"model":[45,126],"encode":[47],"input":[49],"obtain":[52],"basic":[53],"representations.":[55],"It":[56,210],"then":[57],"introduces":[58],"composed":[61],"multi-dimensional":[63],"factors":[65,142],"integrates":[67],"them":[68],"with":[69,81],"features":[71,119],"through":[72],"learnable":[74],"combination":[75],"mechanism,":[76],"which":[77],"forms":[78],"task-related":[79],"representations":[80,95],"clear":[82],"boundaries":[83],"latent":[86],"space.":[87],"To":[88],"further":[89],"strengthen":[90],"consistency":[92],"between":[93,117],"semantics,":[98],"method":[100,227],"constructs":[101],"embedding":[105],"matrix":[106],"employs":[108],"cross-space":[110],"alignment":[111],"mechanism":[112],"ensure":[114],"stable":[115,229],"matching":[116],"textual":[118],"attributes.":[122],"In":[123],"addition,":[124],"applies":[127],"prompt":[128,168,196],"orthogonality":[129],"constraints":[130],"joint":[133],"objective":[135],"maintain":[137],"independence":[138],"across":[139],"different":[140,187],"prompts,":[145],"allowing":[146],"provide":[151],"transparent":[152],"controllable":[154],"guidance":[155],"for":[156,243],"classification":[157],"decisions.":[158],"Three":[159],"types":[160],"sensitivity":[162],"experiments,":[163],"including":[164],"learning":[165],"rate":[166],"sensitivity,":[167,170,174],"length":[169],"data":[172,234],"scale":[173],"are":[175],"designed":[176],"evaluate":[178],"stability":[180],"robustness":[182],"Experimental":[189],"results":[190],"show":[191],"that":[192],"proposed":[194],"effectively":[199],"alleviates":[200],"conflicts":[202],"ambiguity":[205],"classification.":[209,246],"significantly":[211],"improves":[212],"performance":[213],"accuracy,":[215],"precision,":[216],"recall,":[217],"AUC,":[219],"demonstrates":[221],"strong":[222],"cross-task":[223],"applicability.":[224],"Overall,":[225],"achieves":[228],"modeling":[231],"limited":[233],"offers":[236],"efficient":[238],"interpretable":[240],"pathway":[242]},"counts_by_year":[],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2026-03-04T00:00:00"}