{"id":"https://openalex.org/W7125961674","doi":"https://doi.org/10.1109/smc58881.2025.11342764","title":"Learning Preference Distributions: A Label-Side Paradigm for Explainable Reward Models","display_name":"Learning Preference Distributions: A Label-Side Paradigm for Explainable Reward Models","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125961674","doi":"https://doi.org/10.1109/smc58881.2025.11342764"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124078836","display_name":"Shikai Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikai Chen","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124109386","display_name":"Jin Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Yuan","raw_affiliation_strings":["AI Lab, Lenovo Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Zhang","raw_affiliation_strings":["AI Lab, Lenovo Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101873354","display_name":"Zhongchao Shi","orcid":"https://orcid.org/0000-0002-5216-3827"},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongchao Shi","raw_affiliation_strings":["AI Lab, Lenovo Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124129987","display_name":"Jianping Fan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210156165","display_name":"Lenovo (China)","ror":"https://ror.org/04srd9d93","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210156165"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Fan","raw_affiliation_strings":["AI Lab, Lenovo Research,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AI Lab, Lenovo Research,Beijing,China","institution_ids":["https://openalex.org/I4210156165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124065713","display_name":"Xin Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Geng","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100728762","display_name":"Yong Rui","orcid":"https://orcid.org/0000-0002-9142-5914"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Rui","raw_affiliation_strings":["Southeast University,School of Computer Science and Engineering,Nanjing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University,School of Computer Science and Engineering,Nanjing,China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"6383","last_page":"6390"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.597599983215332,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.597599983215332,"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":0.040800001472234726,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.03700000047683716,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/preference","display_name":"Preference","score":0.6097000241279602},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.6055999994277954},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.491100013256073},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.42980000376701355},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.38909998536109924},{"id":"https://openalex.org/keywords/human-dimension","display_name":"Human Dimension","score":0.3833000063896179},{"id":"https://openalex.org/keywords/preference-learning","display_name":"Preference learning","score":0.3831999897956848},{"id":"https://openalex.org/keywords/probability-distribution","display_name":"Probability distribution","score":0.3765999972820282},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.3702000081539154}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6097000241279602},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6055999994277954},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4952000081539154},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.491100013256073},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4893999993801117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44110000133514404},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.42980000376701355},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C2779641649","wikidata":"https://www.wikidata.org/wiki/Q18377767","display_name":"Human Dimension","level":3,"score":0.3833000063896179},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3831999897956848},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.34200000762939453},{"id":"https://openalex.org/C119322782","wikidata":"https://www.wikidata.org/wiki/Q2662236","display_name":"VC dimension","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C30732413","wikidata":"https://www.wikidata.org/wiki/Q17092636","display_name":"Intrinsic dimension","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.30160000920295715},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2881999909877777},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C202889954","wikidata":"https://www.wikidata.org/wiki/Q1139554","display_name":"Subjectivity","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C98385598","wikidata":"https://www.wikidata.org/wiki/Q1339385","display_name":"Empirical distribution function","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.2540999948978424},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342764","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342764","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4429282248020172,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2330485005","https://openalex.org/W2553156677","https://openalex.org/W2565649476","https://openalex.org/W2763110165","https://openalex.org/W2807904173","https://openalex.org/W2905064233","https://openalex.org/W2965880440","https://openalex.org/W2981059842","https://openalex.org/W3034504038","https://openalex.org/W4404792842"],"related_works":[],"abstract_inverted_index":{"The":[0],"reward":[1],"model":[2],"is":[3,29],"a":[4,74,113,159],"critical":[5],"component":[6],"in":[7,23,67],"training":[8],"powerful":[9],"large":[10],"language":[11],"models.":[12],"However,":[13],"current":[14],"methods":[15,38],"largely":[16],"overlook":[17],"the":[18,59,105,119],"inherent":[19],"subjectivity":[20],"and":[21,51,63,121,131,141,165],"variability":[22],"human":[24,68,81,125],"preferences.":[25],"Typically,":[26],"this":[27],"issue":[28],"indirectly":[30],"addressed":[31],"through":[32],"model-side":[33],"approaches,":[34],"such":[35],"as":[36],"ensemble":[37],"to":[39,48,57,91,112],"estimate":[40],"uncertainty":[41,163],"from":[42,88],"multiple":[43],"predictions":[44],"or":[45],"uncertainty-aware":[46],"regression":[47],"predict":[49],"mean":[50],"variance.":[52],"These":[53],"indirect":[54],"approaches":[55],"fail":[56],"capture":[58],"intrinsic":[60],"distributional":[61],"characteristics":[62],"inter-rater":[64],"disagreements":[65],"present":[66],"judgments.":[69],"In":[70],"contrast,":[71],"we":[72],"propose":[73],"direct,":[75],"label-side":[76],"solution":[77],"by":[78],"explicitly":[79,110],"modeling":[80],"preference":[82,115,167],"distributions.":[83],"We":[84],"recover":[85],"missing":[86],"information":[87],"scalar":[89],"ratings":[90],"construct":[92],"meaningful":[93],"distribution":[94,109],"labels.":[95],"By":[96],"employing":[97],"Label":[98],"Distribution":[99],"Learning":[100],"(LDL),":[101],"each":[102],"dimension":[103],"of":[104,124],"resulting":[106],"multidimensional":[107,122],"discrete":[108],"corresponds":[111],"specific":[114],"score,":[116],"naturally":[117],"reflecting":[118],"subjective":[120],"nature":[123],"evaluations.":[126],"Our":[127],"approach":[128],"improves":[129],"explainability":[130],"confidence":[132],"estimation,":[133],"while":[134],"also":[135,157],"enabling":[136],"more":[137],"effective":[138],"data":[139],"selection":[140],"sample-efficient":[142],"test-time":[143],"adaptation.":[144],"Empirical":[145],"results":[146],"demonstrate":[147],"that":[148],"our":[149],"method":[150],"not":[151],"only":[152],"achieves":[153],"state-of-the-art":[154],"performance":[155],"but":[156],"provides":[158],"robust":[160],"framework":[161],"for":[162],"quantification":[164],"nuanced":[166],"modeling.":[168]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}