{"id":"https://openalex.org/W7203701574","doi":"https://doi.org/10.48550/arxiv.2608.14828","title":"MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment","display_name":"MINT: Min-Selection Preference Distillation for Balanced Multi-Objective Alignment","publication_year":2026,"publication_date":"2026-08-14","ids":{"openalex":"https://openalex.org/W7203701574","doi":"https://doi.org/10.48550/arxiv.2608.14828"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.14828","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14828","pdf_url":"https://arxiv.org/pdf/2608.14828","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.14828","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5147415729","display_name":"Tony Tu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I4210149135","display_name":"Zillow Group (United States)","ror":"https://ror.org/03n86v874","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tu, Tony","raw_affiliation_strings":["Georgia Institute of Technology","Zillow Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Zillow Group","institution_ids":["https://openalex.org/I4210149135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144236694","display_name":"Sayan Chakraborty","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210149135","display_name":"Zillow Group (United States)","ror":"https://ror.org/03n86v874","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chakraborty, Sayan","raw_affiliation_strings":["Zillow Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zillow Group","institution_ids":["https://openalex.org/I4210149135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125103998","display_name":"Ruomeng Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210149135","display_name":"Zillow Group (United States)","ror":"https://ror.org/03n86v874","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Ruomeng","raw_affiliation_strings":["Zillow Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zillow Group","institution_ids":["https://openalex.org/I4210149135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016194960","display_name":"Tony Qin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210149135","display_name":"Zillow Group (United States)","ror":"https://ror.org/03n86v874","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qin, Tony","raw_affiliation_strings":["Zillow Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zillow Group","institution_ids":["https://openalex.org/I4210149135"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071834523","display_name":"Austin Tian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210149135","display_name":"Zillow Group (United States)","ror":"https://ror.org/03n86v874","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tian, Austin","raw_affiliation_strings":["Zillow Group"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zillow Group","institution_ids":["https://openalex.org/I4210149135"]}]}],"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":true,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7031000256538391,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7031000256538391,"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":0.10580000281333923,"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":0.02590000070631504,"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/generalized-means","display_name":"generalized means","score":0.6380000114440918},{"id":"https://openalex.org/keywords/dpo","display_name":"DPO","score":0.4970000088214874}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6751999855041504},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6299999952316284},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5925999879837036},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.47049999237060547},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4691999852657318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45840001106262207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4361000061035156},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.37779998779296875},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3540000021457672},{"id":"https://openalex.org/C7321624","wikidata":"https://www.wikidata.org/wiki/Q205","display_name":"Infinity","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.3384999930858612},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3303999900817871},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C2779545769","wikidata":"https://www.wikidata.org/wiki/Q5135364","display_name":"Closeness","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2721000015735626},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.25360000133514404}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.14828","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14828","pdf_url":"https://arxiv.org/pdf/2608.14828","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.14828","doi":"https://doi.org/10.48550/arxiv.2608.14828","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.14828","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.14828","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.14828","pdf_url":"https://arxiv.org/pdf/2608.14828","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203701574.pdf","grobid_xml":"https://content.openalex.org/works/W7203701574.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W4223908421","https://openalex.org/W4226278401","https://openalex.org/W4366196653","https://openalex.org/W4377121527","https://openalex.org/W4391901224","https://openalex.org/W7133208539"],"related_works":["https://openalex.org/W7220745058","https://openalex.org/W7123946233","https://openalex.org/W4416613238","https://openalex.org/W7161044514","https://openalex.org/W4404783337","https://openalex.org/W4417093398","https://openalex.org/W7127351271","https://openalex.org/W7127437642","https://openalex.org/W7171360228","https://openalex.org/W4416052740"],"abstract_inverted_index":{"Aligning":[0],"a":[1,10,35,66,78,113],"language":[2],"agent":[3,37],"to":[4,28,39,69,118,147,173],"several":[5],"objectives":[6,18,131],"at":[7],"once":[8],"is":[9,26,50,105],"persistent":[11],"failure":[12],"mode":[13],"of":[14,58,81,112],"preference-based":[15],"training:":[16],"when":[17],"are":[19],"combined":[20],"additively,":[21],"optimization":[22],"collapses":[23],"onto":[24],"whichever":[25],"cheapest":[27],"improve":[29],"and":[30,125,155,180],"sacrifices":[31],"the":[32,91,95,106,142,176],"rest,":[33],"so":[34],"support":[36,124,139],"learns":[38],"sound":[40],"warm":[41],"while":[42,132],"giving":[43],"no":[44,56],"real":[45],"help.":[46],"The":[47],"root":[48],"issue":[49],"that":[51,191],"an":[52,100,185],"additive":[53,117],"reward":[54],"has":[55],"notion":[57],"balance.":[59],"We":[60],"introduce":[61],"Mint":[62],"(MIN-selection":[63],"preference":[64,70],"disTillation),":[65],"one-line":[67],"change":[68],"distillation:":[71],"rather":[72],"than":[73],"ranking":[74],"sampled":[75],"candidates":[76],"by":[77,86],"weighted":[79],"sum":[80],"rewards,":[82],"we":[83],"rank":[84],"them":[85],"their":[87,135],"weakest":[88],"objective,":[89],"distilling":[90],"best-balanced":[92],"candidate":[93],"over":[94,184],"most":[96],"lopsided":[97],"one":[98],"with":[99],"unchanged":[101],"DPO":[102],"objective.":[103],"This":[104],"p":[107],"->":[108],"negative":[109],"infinity":[110],"limit":[111],"generalized-mean":[114],"family":[115],"spanning":[116],"worst-case":[119],"selection.":[120],"Across":[121],"cooperative":[122],"emotional":[123,138],"adversarial":[126],"negotiation,":[127],"min-selection":[128,168],"lifts":[129],"both":[130],"sharply":[133],"cutting":[134],"imbalance;":[136],"on":[137],"it":[140],"raises":[141],"weaker":[143],"axis":[144],"from":[145],"0.37":[146],"0.64":[148],"(p":[149],"<":[150],"10^-40),":[151],"surpassing":[152],"human":[153],"experts":[154],"persisting":[156],"across":[157],"full":[158],"multi-turn":[159],"rollouts.":[160],"A":[161],"turn-by-turn":[162],"analysis":[163],"yields":[164],"our":[165],"central":[166],"finding:":[167],"corrects":[169],"imbalance":[170,192],"in":[171],"proportion":[172],"how":[174],"imbalanced":[175],"reference":[177],"policy":[178],"is,":[179],"its":[181],"benefit":[182],"endures":[183],"interaction":[186],"precisely":[187],"as":[188,190],"long":[189],"does.":[193]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-19T00:00:00"}