{"id":"https://openalex.org/W4416036024","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1057","title":"Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce","display_name":"Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416036024","doi":"https://doi.org/10.18653/v1/2025.emnlp-main.1057"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1057","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1057","pdf_url":"https://aclanthology.org/2025.emnlp-main.1057.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.emnlp-main.1057.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079882183","display_name":"Haojin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Haojin Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101563385","display_name":"Zining Zhu","orcid":"https://orcid.org/0000-0003-0854-5382"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zining Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037519114","display_name":"Freda Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Freda Shi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5079882183"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37500664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20915","last_page":"20928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.23690000176429749,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12090","display_name":"Language and cultural evolution","score":0.23690000176429749,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2312999963760376,"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":0.04190000146627426,"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/expressivity","display_name":"Expressivity","score":0.656499981880188},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.4300000071525574},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3767000138759613},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.32330000400543213},{"id":"https://openalex.org/keywords/gamma-distribution","display_name":"Gamma distribution","score":0.31949999928474426},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.2992999851703644}],"concepts":[{"id":"https://openalex.org/C92811239","wikidata":"https://www.wikidata.org/wiki/Q20998670","display_name":"Expressivity","level":2,"score":0.656499981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5985000133514404},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44029998779296875},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43939998745918274},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3767000138759613},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C149717495","wikidata":"https://www.wikidata.org/wiki/Q117806","display_name":"Gamma distribution","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C42337464","wikidata":"https://www.wikidata.org/wiki/Q5532478","display_name":"Generalized gamma distribution","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.emnlp-main.1057","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1057","pdf_url":"https://aclanthology.org/2025.emnlp-main.1057.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.emnlp-main.1057","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.emnlp-main.1057","pdf_url":"https://aclanthology.org/2025.emnlp-main.1057.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 2025 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1597412403","display_name":null,"funder_award_id":"RGPIN-","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G3033334534","display_name":null,"funder_award_id":"AI Chair","funder_id":"https://openalex.org/F4320309949","funder_display_name":"Canadian Institute for Advanced Research"},{"id":"https://openalex.org/G5784215521","display_name":null,"funder_award_id":"Chair","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G6221715925","display_name":null,"funder_award_id":"RGPIN","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8105784103","display_name":null,"funder_award_id":"RGPIN-202","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320309949","display_name":"Canadian Institute for Advanced Research","ror":"https://ror.org/01sdtdd95"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416036024.pdf","grobid_xml":"https://content.openalex.org/works/W4416036024.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autoregressive":[0],"neural":[1],"language":[2],"models":[3],"(LMs)":[4],"generate":[5],"a":[6,16,55,63],"probability":[7,26,157],"distribution":[8,47,64,158],"over":[9,48],"tokens":[10],"at":[11],"each":[12],"time":[13],"step":[14],"given":[15],"prompt.In":[17],"this":[18],"work,":[19],"we":[20,51],"attempt":[21,52],"to":[22,39,53,61,69,103,123,136],"systematically":[23],"understand":[24],"the":[25,49,59,70,114,146,151],"distributions":[27,35,93,112,127],"that":[28,33,57,89],"LMs":[29,131,149],"can":[30],"produce,":[31],"showing":[32],"some":[34],"are":[36,101,121],"significantly":[37],"harder":[38],"elicit":[40],"than":[41,105,138],"others.Specifically,":[42],"for":[43],"any":[44],"target":[45,126],"next-token":[46],"vocabulary,":[50],"find":[54,88],"prompt":[56,86],"induces":[58],"LM":[60],"output":[62],"as":[65,67,156],"close":[66],"possible":[68],"target,":[71],"using":[72,154],"either":[73],"soft":[74],"(Li":[75],"and":[76,150],"Liang,":[77],"2021)":[78],"or":[79,97],"hard":[80],"(Wallace":[81],"et":[82],"al.,":[83],"2019)":[84],"gradient-based":[85],"tuning.We":[87],"(1)":[90],"in":[91],"general,":[92],"with":[94,107,113,132],"very":[95,98],"low":[96],"high":[99],"entropy":[100],"easier":[102,122,135],"approximate":[104,137],"those":[106,117],"moderate":[108],"entropy;":[109],"(2)":[110],"among":[111],"same":[115],"entropy,":[116],"containing":[118],"\"outlier":[119],"tokens\"":[120],"approximate;":[124],"(3)":[125],"generated":[128],"by":[129],"LMs-even":[130],"different":[133],"tokenizers-are":[134],"randomly":[139],"chosen":[140],"targets.These":[141],"results":[142],"offer":[143],"insights":[144],"into":[145],"expressiveness":[147],"of":[148,153],"challenges":[152],"them":[155],"proposers.":[159]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-11-08T00:00:00"}