{"id":"https://openalex.org/W7155417618","doi":"https://doi.org/10.48550/arxiv.2604.20216","title":"Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context","display_name":"Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155417618","doi":"https://doi.org/10.48550/arxiv.2604.20216"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.20216","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20216","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.20216","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134452515","display_name":"Yilun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yilun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019578467","display_name":"Yuan Zhuang","orcid":"https://orcid.org/0000-0003-4792-1985"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080114650","display_name":"Nikhita Vedula","orcid":"https://orcid.org/0000-0003-4857-5308"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vedula, Nikhita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007853790","display_name":"Dushyanta Dhyani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhyani, Dushyanta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071261572","display_name":"Shaoyuan Xu","orcid":"https://orcid.org/0000-0003-3740-2276"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Shaoyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042533495","display_name":"Moyan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Moyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091599934","display_name":"Mohsen Bayati","orcid":"https://orcid.org/0000-0002-7280-912X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bayati, Mohsen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134438751","display_name":"Bryan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bryan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5059403175","display_name":"Shervin Malmasi","orcid":"https://orcid.org/0000-0001-6250-5571"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malmasi, Shervin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.28600001335144043,"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":0.28600001335144043,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.11860000342130661,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.08730000257492065,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/quantile","display_name":"Quantile","score":0.8977000117301941},{"id":"https://openalex.org/keywords/quantile-regression","display_name":"Quantile regression","score":0.6940000057220459},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5986999869346619},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5461000204086304},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.47510001063346863},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3716000020503998},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3612000048160553}],"concepts":[{"id":"https://openalex.org/C118671147","wikidata":"https://www.wikidata.org/wiki/Q578714","display_name":"Quantile","level":2,"score":0.8977000117301941},{"id":"https://openalex.org/C63817138","wikidata":"https://www.wikidata.org/wiki/Q3455889","display_name":"Quantile regression","level":2,"score":0.6940000057220459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6098999977111816},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5986999869346619},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5461000204086304},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.41179999709129333},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37470000982284546},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3716000020503998},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C43555835","wikidata":"https://www.wikidata.org/wiki/Q2300258","display_name":"Conditional probability distribution","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30329999327659607},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28540000319480896},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26930001378059387}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.20216","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20216","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.20216","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.20216","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Many":[0],"applications":[1],"of":[2,45,52,57,146],"LLM-based":[3],"text":[4],"regression":[5,21],"require":[6],"predicting":[7],"a":[8,14,42],"full":[9],"conditional":[10],"distribution":[11,38,61],"rather":[12],"than":[13],"single":[15],"point":[16],"value.":[17],"We":[18,47,113,139],"study":[19],"distributional":[20,154],"under":[22],"empirical-quantile":[23],"supervision,":[24],"where":[25,203],"each":[26,109,156],"input":[27,102],"is":[28,39,91],"paired":[29],"with":[30,119,133,167,179,193],"multiple":[31],"observed":[32],"quantile":[33,77,98,110,117,150,177,204],"outcomes,":[34],"and":[35,63,76,126,163,188,199,209],"the":[36,55,64,92,101,142,160],"target":[37],"represented":[40],"by":[41],"dense":[43],"grid":[44],"quantiles.":[46],"address":[48],"two":[49],"key":[50],"limitations":[51],"current":[53],"approaches:":[54],"lack":[56],"local":[58,134],"grounding":[59],"for":[60,108,149],"estimates,":[62],"reliance":[65],"on":[66,159,197],"shared":[67],"representations":[68],"that":[69,176],"create":[70],"an":[71],"indirect":[72],"bottleneck":[73],"between":[74],"inputs":[75],"outputs.":[78],"In":[79],"this":[80],"paper,":[81],"we":[82],"introduce":[83],"Quantile":[84],"Token":[85],"Regression,":[86],"which,":[87],"to":[88,95,130,172],"our":[89],"knowledge,":[90],"first":[93,143],"work":[94],"insert":[96],"dedicated":[97],"tokens":[99,118,178,205],"into":[100],"sequence,":[103],"enabling":[104],"direct":[105],"input-output":[106],"pathways":[107],"through":[111],"self-attention.":[112],"further":[114],"augment":[115],"these":[116],"retrieval,":[120],"incorporating":[121],"semantically":[122],"similar":[123,137],"neighbor":[124],"instances":[125],"their":[127],"empirical":[128],"distributions":[129],"ground":[131],"predictions":[132],"evidence":[135],"from":[136,170],"instances.":[138],"also":[140],"provide":[141],"theoretical":[144],"analysis":[145],"loss":[147],"functions":[148],"regression,":[151],"clarifying":[152],"which":[153],"objectives":[155],"optimizes.":[157],"Experiments":[158],"Inside":[161],"Airbnb":[162],"StackSample":[164],"benchmark":[165],"datasets":[166,202],"LLMs":[168],"ranging":[169],"1.7B":[171],"14B":[173],"parameters":[174],"show":[175],"neighbors":[180],"consistently":[181],"outperform":[182],"baselines":[183],"(~4":[184],"points":[185],"lower":[186],"MAPE":[187],"2x":[189],"narrower":[190],"prediction":[191],"intervals),":[192],"especially":[194],"large":[195],"gains":[196],"smaller":[198],"more":[200,210],"challenging":[201],"produce":[206],"substantially":[207],"sharper":[208],"accurate":[211],"distributions.":[212]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-24T00:00:00"}