{"id":"https://openalex.org/W7224967139","doi":"https://doi.org/10.48550/arxiv.2610.39372","title":"Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models","display_name":"Cord: Confidence-Anchored Order Residual Decoding for Masked Diffusion Language Models","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224967139","doi":"https://doi.org/10.48550/arxiv.2610.39372"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39372","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39372","pdf_url":"https://arxiv.org/pdf/2610.39372","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39372","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5158775604","display_name":"Chengwei Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Chengwei","raw_affiliation_strings":["Case Western Reserve University , Cleveland , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Western Reserve University , Cleveland , USA","institution_ids":["https://openalex.org/I58956616"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023907236","display_name":"Zhaoyan Jia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia, Zhaoyan","raw_affiliation_strings":["University of Southern California , Los Angeles , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California , Los Angeles , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044650311","display_name":"Massoud Pedram","orcid":"https://orcid.org/0000-0002-2677-7307","observed_orcids":["https://orcid.org/0000-0002-2677-7307"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pedram, Massoud","raw_affiliation_strings":["University of Southern California , Los Angeles , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California , Los Angeles , USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113244321","display_name":"Gourav Datta","orcid":"https://orcid.org/0000-0002-5380-2619","observed_orcids":["https://orcid.org/0000-0002-5380-2619"]},"institutions":[{"id":"https://openalex.org/I58956616","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666","country_code":"US","type":"education","lineage":["https://openalex.org/I58956616"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Datta, Gourav","raw_affiliation_strings":["Case Western Reserve University , Cleveland , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Case Western Reserve University , Cleveland , USA","institution_ids":["https://openalex.org/I58956616"]}]}],"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/T10028","display_name":"Topic Modeling","score":0.4887999892234802,"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":0.4887999892234802,"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":0.46560001373291016,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.00570000009611249,"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/masked-diffusion-language-models","display_name":"masked diffusion language models","score":0.9729999899864197},{"id":"https://openalex.org/keywords/decoding-order","display_name":"decoding order","score":0.890999972820282},{"id":"https://openalex.org/keywords/contextual-bandits","display_name":"contextual bandits","score":0.7519999742507935},{"id":"https://openalex.org/keywords/generation-quality","display_name":"generation quality","score":0.4090000092983246},{"id":"https://openalex.org/keywords/code-generation","display_name":"code generation","score":0.878000020980835},{"id":"https://openalex.org/keywords/constraint-satisfaction","display_name":"constraint satisfaction","score":0.9710000157356262}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.8507000207901001},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6761000156402588},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6047000288963318},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5511000156402588},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5292999744415283},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5174000263214111},{"id":"https://openalex.org/C204397858","wikidata":"https://www.wikidata.org/wiki/Q4437907","display_name":"List decoding","level":5,"score":0.4424999952316284},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.41839998960494995},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36489999294281006},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34470000863075256},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.32910001277923584},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2858999967575073},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26510000228881836},{"id":"https://openalex.org/C193969084","wikidata":"https://www.wikidata.org/wiki/Q7452500","display_name":"Sequential decoding","level":4,"score":0.26019999384880066},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.257999986410141},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39372","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39372","pdf_url":"https://arxiv.org/pdf/2610.39372","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.2610.39372","doi":"https://doi.org/10.48550/arxiv.2610.39372","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39372","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39372","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39372","pdf_url":"https://arxiv.org/pdf/2610.39372","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224967139.pdf","grobid_xml":"https://content.openalex.org/works/W7224967139.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415334935","https://openalex.org/W7128723489","https://openalex.org/W7166638395","https://openalex.org/W7166799922","https://openalex.org/W4416156711","https://openalex.org/W7214976080","https://openalex.org/W7220962774","https://openalex.org/W7214781100","https://openalex.org/W7163182386","https://openalex.org/W7165638297"],"abstract_inverted_index":{"The":[0,89],"decoding":[1,62,110,164],"order":[2],"of":[3],"masked":[4],"diffusion":[5],"language":[6],"models":[7],"(dLLMs)":[8],"can":[9,37],"substantially":[10],"affect":[11],"generation":[12,80],"quality,":[13],"yet":[14],"common":[15],"decoders":[16],"typically":[17],"apply":[18],"the":[19,94,97,171,180],"same":[20],"reveal":[21,126,188],"rule":[22],"throughout":[23],"generation.":[24],"Confidence":[25],"provides":[26],"a":[27,35,55,64,104,114,130],"strong":[28],"default,":[29],"but":[30],"it":[31,75],"measures":[32],"how":[33,42,71],"decisively":[34],"position":[36,46],"be":[38,48],"predicted":[39],"now,":[40],"not":[41],"useful":[43],"revealing":[44],"that":[45,59,179],"will":[47],"for":[49],"subsequent":[50],"decoding.":[51],"We":[52],"propose":[53],"Cord,":[54],"lightweight":[56],"prompt-conditioned":[57],"policy":[58,106],"retains":[60],"confidence":[61,163],"as":[63],"stable":[65],"reference":[66],"and":[67,70,86,96,148,152,167,190,205],"learns":[68],"when":[69],"to":[72,83,92,165],"depart":[73],"from":[74,135,160],"through":[76],"geometric":[77],"residuals":[78,90,182],"over":[79,170],"direction,":[81],"proximity":[82],"revealed":[84],"context,":[85],"two-sided":[87,191],"infilling.":[88,192],"adapt":[91],"both":[93],"prompt":[95],"evolving":[98],"partial":[99],"response.":[100],"Rather":[101],"than":[102],"sampling":[103],"new":[105],"action":[107],"at":[108],"every":[109],"step,":[111],"Cord":[112,155,193],"samples":[113],"single":[115],"low-dimensional":[116],"coefficient":[117],"matrix":[118],"per":[119],"rollout,":[120],"which":[121],"induces":[122],"an":[123],"entire":[124],"state-dependent":[125],"trajectory.":[127],"This":[128],"yields":[129],"contextual-bandit":[131],"formulation":[132],"trained":[133],"directly":[134],"sequence-level":[136],"rewards,":[137],"without":[138],"step-level":[139],"credit":[140],"assignment":[141],"or":[142],"backbone":[143,202],"updates.":[144],"Across":[145],"three":[146],"dLLMs":[147],"five":[149],"reasoning,":[150],"code,":[151],"constraint-satisfaction":[153],"benchmarks,":[154],"improves":[156,169],"average":[157],"task":[158],"success":[159],"32.0%":[161],"under":[162],"48.2%,":[166],"further":[168],"best":[172],"per-domain":[173],"fixed":[174],"residual.":[175],"Behavioral":[176],"audits":[177],"show":[178],"learned":[181],"induce":[183],"substantial,":[184],"task-dependent":[185],"changes":[186],"in":[187],"locality":[189],"adds":[194],"only":[195,207],"$0.53$M":[196],"trainable":[197],"parameters,":[198],"requires":[199],"no":[200],"additional":[201],"forward":[203],"passes,":[204],"incurs":[206],"5.39%":[208],"inference":[209],"latency":[210],"overhead.":[211]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-10-31T00:00:00"}