{"id":"https://openalex.org/W7129088285","doi":"https://doi.org/10.48550/arxiv.2602.12660","title":"Learning Ordinal Probabilistic Reward from Preferences","display_name":"Learning Ordinal Probabilistic Reward from Preferences","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7129088285","doi":"https://doi.org/10.48550/arxiv.2602.12660"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.12660","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126152058","display_name":"Longze Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Longze","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126123080","display_name":"Lu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120034779","display_name":"Renke Shan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan, Renke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058169437","display_name":"Ze Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Ze","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126101824","display_name":"Run Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Run","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126134825","display_name":"Jiaming Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiaming","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126091596","display_name":"Jing Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Jing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126124110","display_name":"Qiyao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qiyao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126156791","display_name":"Min Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Min","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5126152058"],"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":0.451200008392334,"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":0.451200008392334,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.1615999937057495,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.051100000739097595,"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/probabilistic-logic","display_name":"Probabilistic logic","score":0.7128999829292297},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6804999709129333},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5584999918937683},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.49480000138282776},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.4803999960422516},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4593000113964081},{"id":"https://openalex.org/keywords/probability-mass-function","display_name":"Probability mass function","score":0.4498000144958496},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4413999915122986}],"concepts":[{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7128999829292297},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6804999709129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6301000118255615},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6098999977111816},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5647000074386597},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5584999918937683},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.49480000138282776},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4593000113964081},{"id":"https://openalex.org/C197096303","wikidata":"https://www.wikidata.org/wiki/Q869887","display_name":"Probability mass function","level":3,"score":0.4498000144958496},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4413999915122986},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4156000018119812},{"id":"https://openalex.org/C143017306","wikidata":"https://www.wikidata.org/wiki/Q3318133","display_name":"Probabilistic relevance model","level":4,"score":0.40149998664855957},{"id":"https://openalex.org/C85461838","wikidata":"https://www.wikidata.org/wiki/Q7100785","display_name":"Ordinal data","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C110313322","wikidata":"https://www.wikidata.org/wiki/Q7100793","display_name":"Ordinal regression","level":2,"score":0.29319998621940613},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2775999903678894},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.2705000042915344},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C122282355","wikidata":"https://www.wikidata.org/wiki/Q7246855","display_name":"Probabilistic forecasting","level":3,"score":0.26339998841285706},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.12660","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.12660","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12660","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.12660","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.780536949634552}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reward":[0,58,102],"models":[1,8],"are":[2],"crucial":[3],"for":[4,82],"aligning":[5],"large":[6],"language":[7],"(LLMs)":[9],"with":[10],"human":[11],"values":[12],"and":[13,179],"intentions.":[14],"Existing":[15],"approaches":[16],"follow":[17],"either":[18],"Generative":[19],"(GRMs)":[20],"or":[21],"Discriminative":[22],"(DRMs)":[23],"paradigms,":[24],"yet":[25],"both":[26],"suffer":[27],"from":[28],"limitations:":[29],"GRMs":[30],"typically":[31],"demand":[32],"costly":[33],"point-wise":[34],"supervision,":[35],"while":[36],"DRMs":[37],"produce":[38],"uncalibrated":[39],"relative":[40,195],"scores":[41],"that":[42,164,189],"lack":[43],"probabilistic":[44],"interpretation.":[45],"To":[46,88],"address":[47],"these":[48],"challenges,":[49],"we":[50,93,120],"introduce":[51],"a":[52,66,74,78,111,122],"novel":[53],"reward":[54,64,160,174],"modeling":[55,63],"paradigm:":[56],"Probabilistic":[57,101],"Model":[59,103],"(PRM).":[60],"Instead":[61],"of":[62,85,114,183],"as":[65,73],"deterministic":[67],"scalar,":[68],"our":[69,165,190],"approach":[70],"treats":[71],"it":[72],"random":[75],"variable,":[76],"learning":[77],"full":[79],"probability":[80,151],"distribution":[81,186],"the":[83,99,107,146,150,184],"quality":[84,108,139],"each":[86],"response.":[87],"make":[89],"this":[90],"paradigm":[91],"practical,":[92],"present":[94],"its":[95],"closed-form,":[96],"discrete":[97],"realization:":[98],"Ordinal":[100],"(OPRM),":[104],"which":[105,144],"discretizes":[106],"score":[109,185],"into":[110],"finite":[112],"set":[113],"ordinal":[115],"ratings.":[116],"Building":[117],"on":[118,158],"OPRM,":[119],"propose":[121],"data-efficient":[123],"training":[124],"strategy":[125],"called":[126],"Region":[127],"Flooding":[128],"Tuning":[129],"(RgFT).":[130],"It":[131],"enables":[132],"rewards":[133],"to":[134,148,172],"better":[135],"reflect":[136],"absolute":[137,199],"text":[138],"by":[140,169],"incorporating":[141],"quality-level":[142],"annotations,":[143],"guide":[145],"model":[147,161],"concentrate":[149],"mass":[152],"within":[153],"corresponding":[154],"rating":[155],"sub-regions.":[156],"Experiments":[157],"various":[159],"benchmarks":[162],"show":[163],"method":[166,191],"improves":[167],"accuracy":[168],"$\\textbf{2.9%}\\sim\\textbf{7.4%}$":[170],"compared":[171],"prior":[173],"models,":[175],"demonstrating":[176],"strong":[177],"performance":[178],"data":[180],"efficiency.":[181],"Analysis":[182],"provides":[187],"evidence":[188],"captures":[192],"not":[193],"only":[194],"rankings":[196],"but":[197],"also":[198],"quality.":[200]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-17T00:00:00"}