{"id":"https://openalex.org/W4385767747","doi":"https://doi.org/10.24963/ijcai.2023/460","title":"On Conditional and Compositional Language Model Differentiable Prompting","display_name":"On Conditional and Compositional Language Model Differentiable Prompting","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385767747","doi":"https://doi.org/10.24963/ijcai.2023/460"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/460","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/460","pdf_url":"https://www.ijcai.org/proceedings/2023/0460.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0460.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049628803","display_name":"Jonathan Pilault","orcid":null},"institutions":[{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jonathan Pilault","raw_affiliation_strings":["MILA, Polytechnique Montr\u00e9al"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MILA, Polytechnique Montr\u00e9al","institution_ids":["https://openalex.org/I45683168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077675371","display_name":"Can Liu","orcid":"https://orcid.org/0000-0003-3267-3317"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Can Liu","raw_affiliation_strings":["Amazon","Amazon Alexa,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Amazon Alexa,","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001987532","display_name":"Mohit Bansal","orcid":"https://orcid.org/0000-0001-5522-1351"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":["University of North Carolina at Chapel Hill"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Carolina at Chapel Hill","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079131136","display_name":"Markus Dreyer","orcid":null},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]},{"id":"https://openalex.org/I4210089985","display_name":"Amazon (Germany)","ror":"https://ror.org/00b9ktm87","country_code":"DE","type":"company","lineage":["https://openalex.org/I1311688040","https://openalex.org/I4210089985"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Markus Dreyer","raw_affiliation_strings":["Amazon","Amazon Alexa,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amazon","institution_ids":["https://openalex.org/I4210089985"]},{"raw_affiliation_string":"Amazon Alexa,","institution_ids":["https://openalex.org/I1311688040"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":"4136","last_page":"4144"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":1.0,"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":1.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9998999834060669,"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":0.9936000108718872,"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":0.8191097378730774},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6781477332115173},{"id":"https://openalex.org/keywords/principle-of-compositionality","display_name":"Principle of compositionality","score":0.6504865884780884},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6367347836494446},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.627045750617981},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5799764394760132},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5743630528450012},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4975924789905548},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4834078848361969},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4760018289089203},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4756878614425659},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42256492376327515},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3394242227077484},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.24048185348510742}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8191097378730774},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6781477332115173},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.6504865884780884},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6367347836494446},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.627045750617981},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5799764394760132},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5743630528450012},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4975924789905548},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4834078848361969},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4760018289089203},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4756878614425659},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42256492376327515},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3394242227077484},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.24048185348510742},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2023/460","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/460","pdf_url":"https://www.ijcai.org/proceedings/2023/0460.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.polymtl.ca:60169","is_oa":false,"landing_page_url":"https://publications.polymtl.ca/60169/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401013","display_name":"PolyPublie (\u00c9cole Polytechnique de Montr\u00e9al)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45683168","host_organization_name":"Polytechnique Montr\u00e9al","host_organization_lineage":["https://openalex.org/I45683168"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Communication de conf\u00e9rence"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/460","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/460","pdf_url":"https://www.ijcai.org/proceedings/2023/0460.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385767747.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W22168010","https://openalex.org/W222053410","https://openalex.org/W2130903752","https://openalex.org/W2557764419","https://openalex.org/W2888482885","https://openalex.org/W2923014074","https://openalex.org/W2963912046","https://openalex.org/W2964303773","https://openalex.org/W2970476646","https://openalex.org/W2970925270","https://openalex.org/W2996132992","https://openalex.org/W3035164270","https://openalex.org/W3043172396","https://openalex.org/W3044438666","https://openalex.org/W3087148478","https://openalex.org/W3098136301","https://openalex.org/W3103616906","https://openalex.org/W3107826490","https://openalex.org/W3127433878","https://openalex.org/W3134412209","https://openalex.org/W3153427360","https://openalex.org/W3154200459","https://openalex.org/W3168867926","https://openalex.org/W3174702398","https://openalex.org/W3174770825","https://openalex.org/W3212455623","https://openalex.org/W4205991051","https://openalex.org/W4229005744","https://openalex.org/W4235073708","https://openalex.org/W4248995229","https://openalex.org/W4287113019","https://openalex.org/W4288089799","https://openalex.org/W4298079254","https://openalex.org/W4298343034","https://openalex.org/W4301259831","https://openalex.org/W4306904382","https://openalex.org/W4309811444","https://openalex.org/W4385245566","https://openalex.org/W4386566893"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W4251923961","https://openalex.org/W1526190050","https://openalex.org/W2477397717","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894"],"abstract_inverted_index":{"Prompts":[0,23],"have":[1],"been":[2],"shown":[3],"to":[4,9,17,59,95,104],"be":[5,25],"an":[6],"effective":[7],"method":[8],"adapt":[10],"a":[11,28,34,50,79],"frozen":[12],"Pretrained":[13],"Language":[14],"Model":[15],"(PLM)":[16],"perform":[18],"well":[19],"on":[20,84,146],"downstream":[21],"tasks.":[22],"can":[24],"represented":[26],"by":[27,33],"human-engineered":[29],"word":[30],"sequence":[31],"or":[32,63],"learned":[35],"continuous":[36,67],"embedding.":[37],"In":[38],"this":[39],"work,":[40],"we":[41],"investigate":[42],"conditional":[43],"and":[44,119,126,129,139,152],"compositional":[45,116,147],"differentiable":[46],"prompting.":[47],"We":[48,122],"propose":[49],"new":[51],"model,":[52],"Prompt":[53],"Production":[54,89],"System":[55],"(ProPS),":[56],"which":[57,91],"learns":[58],"transform":[60],"task":[61],"instructions":[62],"input":[64,110],"metadata,":[65],"into":[66],"prompts":[68],"that":[69,102,131],"elicit":[70],"task-specific":[71],"outputs":[72],"from":[73],"the":[74,93],"PLM.":[75],"Our":[76],"model":[77,94],"uses":[78],"modular":[80],"network":[81],"structure":[82],"based":[83],"our":[85],"neural":[86,100],"formulation":[87],"of":[88],"Systems,":[90],"allows":[92],"learn":[96,103],"discrete":[97],"rules":[98],"--":[99],"functions":[101],"specialize":[105],"in":[106],"transforming":[107],"particular":[108],"prompt":[109],"patterns,":[111],"making":[112],"it":[113],"suitable":[114],"for":[115],"transfer":[117],"learning":[118],"few-shot":[120],"learning.":[121],"present":[123],"extensive":[124],"empirical":[125],"theoretical":[127],"analysis":[128],"show":[130],"ProPS":[132],"consistently":[133],"surpasses":[134],"other":[135],"PLM":[136],"adaptation":[137],"techniques,":[138],"often":[140],"improves":[141],"upon":[142],"fully":[143],"fine-tuned":[144],"models,":[145],"generalization":[148],"tasks,":[149],"controllable":[150],"summarization":[151],"multilingual":[153],"translation,":[154],"while":[155],"needing":[156],"fewer":[157],"trainable":[158],"parameters.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}