{"id":"https://openalex.org/W7166882274","doi":"https://doi.org/10.18653/v1/2026.acl-long.555","title":"LLM-SLM Collaborative Framework of Idiomatic Expression Generation","display_name":"LLM-SLM Collaborative Framework of Idiomatic Expression Generation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166882274","doi":"https://doi.org/10.18653/v1/2026.acl-long.555"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.555","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.555","pdf_url":"https://aclanthology.org/2026.acl-long.555.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.555.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139738247","display_name":"Hui Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Gao","raw_affiliation_strings":["School of Computer Science and Technology , Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I132369690","https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139792430","display_name":"Changhao Song","orcid":null},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changhao Song","raw_affiliation_strings":["School of Computer Science and Technology , Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I132369690","https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139838805","display_name":"Peng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Zhang","raw_affiliation_strings":["School of Computer Science and Technology , Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I132369690","https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139762084","display_name":"Zhang Jing","orcid":null},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["School of Computer Science and Technology , Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I132369690","https://openalex.org/I136765683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139835423","display_name":"Chang Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chang Yang","raw_affiliation_strings":["School of Computer Science and Technology , Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I132369690","https://openalex.org/I136765683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139758509","display_name":"Liuxian Ge","orcid":null},"institutions":[{"id":"https://openalex.org/I132369690","display_name":"Tianjin University of Science and Technology","ror":"https://ror.org/018rbtf37","country_code":"CN","type":"education","lineage":["https://openalex.org/I132369690"]},{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liuxian Ge","raw_affiliation_strings":["School of Computer Science and Technology , Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I132369690","https://openalex.org/I136765683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83999794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12125","last_page":"12145"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5074999928474426,"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":0.5074999928474426,"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/T12031","display_name":"Speech and dialogue systems","score":0.18330000340938568,"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":0.0885000005364418,"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/expression","display_name":"Expression (computer science)","score":0.5205000042915344},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3264999985694885},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.30869999527931213},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.25940001010894775},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2581999897956848}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.545799970626831},{"id":"https://openalex.org/C90559484","wikidata":"https://www.wikidata.org/wiki/Q778379","display_name":"Expression (computer science)","level":2,"score":0.5205000042915344},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3790999948978424},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37070000171661377},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3264999985694885},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.29649999737739563},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.555","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.555","pdf_url":"https://aclanthology.org/2026.acl-long.555.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.555","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.555","pdf_url":"https://aclanthology.org/2026.acl-long.555.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5760374524","display_name":null,"funder_award_id":"62276188","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7142792453","display_name":null,"funder_award_id":"62550068","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/W7166882274.pdf","grobid_xml":"https://content.openalex.org/works/W7166882274.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Idiomatic":[0],"Expression":[1],"Generation,":[2],"which":[3],"aims":[4],"to":[5],"produce":[6],"idiomatic":[7,53],"text":[8],"from":[9,22],"plain":[10,67],"text,":[11],"is":[12],"a":[13,101,116,125,156],"valuable":[14],"yet":[15],"challenging":[16],"NLP":[17],"task.However,":[18],"existing":[19],"methods":[20],"suffer":[21],"the":[23,60,78,149],"scarcity":[24],"of":[25,104,153],"parallel":[26,63,106],"data":[27,55,162],"and":[28,66,140,145,151],"dependence":[29],"on":[30,113],"high-quality":[31],"manual":[32],"annotations.To":[33],"address":[34],"this,":[35],"we":[36],"propose":[37],"an":[38],"iterative":[39],"LLM-SLM":[40,165],"(Large":[41],"Language":[42,44],"Model-Small":[43],"Model)":[45],"collaborative":[46],"framework-Auto-IDEA,":[47],"that":[48],"replaces":[49],"human":[50,146],"supervision":[51],"for":[52,94,159],"expression":[54],"generation.In":[56],"this":[57],"self-improving":[58],"cycle,":[59],"LLM":[61],"constructs":[62],"corpora":[64,82],"(idiomatic":[65],"text)":[68],"via":[69],"bidirectional":[70],"semantic":[71],"reconstruction,":[72],"automatically":[73],"generating":[74],"\"Locate-Then-Polish\"":[75],"(LTP)":[76],"annotations;":[77],"SLM":[79],"filters":[80],"low-quality":[81],"while":[83],"continuously":[84],"enhancing":[85],"its":[86],"verification":[87],"ability":[88],"through":[89,164],"incremental":[90],"learning.We":[91],"instantiate":[92],"Auto-IDEA":[93],"Chinese":[95,136],"Idiom":[96,119],"Polishing":[97,120],"(CIP),":[98],"constructing":[99],"CIP-200K,":[100],"largescale":[102],"dataset":[103],"206K":[105],"sentences":[107],"with":[108],"LTP":[109],"annotations.The":[110],"Qwen3-8B":[111],"fine-tuned":[112],"CIP-200K":[114],"achieves":[115],"25.2%":[117],"absolute":[118],"Accuracy":[121],"(IPA)":[122],"improvement":[123],"over":[124],"supervised":[126],"fine-tuning":[127],"(SFT)":[128],"baseline,":[129],"outperforming":[130],"DeepSeek-R1":[131],"by":[132],"6.2%.Extensive":[133],"experiments":[134],"(e.g.,":[135],"idiom":[137,142],"cloze":[138],"tests":[139],"English":[141],"generation":[143,163],"tasks)":[144],"evaluations":[147],"verify":[148],"generalization":[150],"effectiveness":[152],"Auto-IDEA,":[154],"demonstrating":[155],"new":[157],"pathway":[158],"high-quality,":[160],"annotation-free":[161],"collaboration.":[166]},"counts_by_year":[],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2026-07-02T00:00:00"}
