{"id":"https://openalex.org/W7167597707","doi":"https://doi.org/10.48550/arxiv.2607.03528","title":"Aligning Language Models with Selective Prediction","display_name":"Aligning Language Models with Selective Prediction","publication_year":2026,"publication_date":"2026-07-03","ids":{"openalex":"https://openalex.org/W7167597707","doi":"https://doi.org/10.48550/arxiv.2607.03528"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.03528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03528","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,"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.2607.03528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060490066","display_name":"Gaoxiang Luo","orcid":"https://orcid.org/0000-0001-6172-9784"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Gaoxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140176149","display_name":"Yifan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020298700","display_name":"Sinian Zhang","orcid":"https://orcid.org/0009-0004-2760-6982"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Sinian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083191585","display_name":"Aryan Deshwal","orcid":"https://orcid.org/0000-0002-0280-6820"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deshwal, Aryan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136249957","display_name":"Ju Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Ju","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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.21089999377727509,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.21089999377727509,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.15289999544620514,"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":0.1348000019788742,"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/flagging","display_name":"Flagging","score":0.8104000091552734},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.6833000183105469},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5726000070571899},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5526000261306763},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5038999915122986},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.45500001311302185},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.37700000405311584},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.375900000333786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8170999884605408},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.8104000091552734},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6833000183105469},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5726000070571899},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5526000261306763},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5440000295639038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.526199996471405},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45500001311302185},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.375900000333786},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.2709999978542328},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.2635999917984009},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.03528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03528","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,"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.2607.03528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03528","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,"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":[{"id":"https://metadata.un.org/sdg/16","score":0.7588648200035095,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"are":[4],"increasingly":[5],"deployed":[6],"as":[7,161],"critical":[8],"decision-making":[9],"components":[10],"in":[11,117],"high-stakes":[12],"real-world":[13],"AI":[14],"systems,":[15],"rendering":[16],"LLM":[17,30,41,83,104,121],"reliability":[18,31,84],"a":[19,36,135,155],"foremost":[20],"practical":[21],"concern.":[22],"In":[23,78],"this":[24],"paper,":[25],"we":[26,100,133],"focus":[27,101,125],"on":[28,64,102,127,176],"enhancing":[29],"through":[32],"selective":[33],"prediction":[34],"(SP),":[35],"strategy":[37],"that":[38,65,124],"allows":[39],"an":[40],"to":[42,51,110,172],"only":[43],"predict":[44],"for":[45,74,141],"inputs":[46,68,73],"where":[47],"it":[48],"is":[49],"likely":[50],"be":[52],"correct":[53],"(i.e.,":[54,62],"coverage)":[55],"and":[56,90,108,179],"hence":[57],"reduce":[58],"the":[59,71,87,103,147,150],"error":[60],"rate":[61],"risk)":[63],"portion":[66],"of":[67],"--":[69,154,160],"flagging":[70],"remaining":[72],"future":[75],"human":[76],"discretion.":[77],"other":[79],"words,":[80],"SP":[81,97,114,157],"improves":[82],"by":[85],"balancing":[86],"risk-coverage":[88,151,169],"trade-off":[89,170],"enabling":[91],"seamless":[92],"human-AI":[93],"collaboration.":[94],"To":[95],"integrate":[96],"into":[98],"LLMs,":[99],"post-training":[105],"alignment":[106,122,137,163,174],"stage":[107],"propose":[109,134],"align":[111],"LLMs":[112],"with":[113,119],"performance":[115,158],"metrics,":[116],"contrast":[118],"existing":[120],"methods":[123],"primarily":[126],"correctness":[128],"or":[129],"calibration":[130],"metrics.":[131],"Specifically,":[132],"novel":[136],"framework,":[138],"Reinforcement":[139],"Learning":[140],"Selection":[142],"Reward":[143],"(RLSR),":[144],"which":[145],"targets":[146],"area":[148],"under":[149],"curve":[152],"(AURC)":[153],"popular":[156],"metric":[159],"its":[162],"objective.":[164],"RLSR":[165],"achieves":[166],"substantially":[167],"better":[168],"compared":[171],"multiple":[173],"baselines":[175],"both":[177],"in-domain":[178],"out-of-domain":[180],"tasks.":[181]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-08T00:00:00"}