{"id":"https://openalex.org/W7133506760","doi":"https://doi.org/10.48550/arxiv.2603.02760","title":"Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration","display_name":"Efficient Self-Evaluation for Diffusion Language Models via Sequence Regeneration","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133506760","doi":"https://doi.org/10.48550/arxiv.2603.02760"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02760","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":null,"license_id":null,"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.2603.02760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128056179","display_name":"Linhao Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Linhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122985968","display_name":"Linyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Linyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128050189","display_name":"Wen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069665198","display_name":"Yuling Xi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi, Yuling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128049976","display_name":"Chenchen Jing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Chenchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128092077","display_name":"Jiaheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiaheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128065684","display_name":"Hao Chen (5190)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128091527","display_name":"Chunhua Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Chunhua","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/T10028","display_name":"Topic Modeling","score":0.5999000072479248,"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":0.5999000072479248,"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":0.12460000067949295,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.02539999969303608,"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/sequence","display_name":"Sequence (biology)","score":0.6266000270843506},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5677000284194946},{"id":"https://openalex.org/keywords/probability-estimation","display_name":"Probability estimation","score":0.5640000104904175},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5616000294685364},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5450000166893005},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44190001487731934},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41690000891685486},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.3950999975204468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7343999743461609},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6266000270843506},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5677000284194946},{"id":"https://openalex.org/C2983703474","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Probability estimation","level":2,"score":0.5640000104904175},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5616000294685364},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4828000068664551},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44190001487731934},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3849000036716461},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3547999858856201},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.352400004863739},{"id":"https://openalex.org/C167928553","wikidata":"https://www.wikidata.org/wiki/Q1376021","display_name":"Estimation theory","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29899999499320984},{"id":"https://openalex.org/C2776292839","wikidata":"https://www.wikidata.org/wiki/Q5179217","display_name":"Coverage probability","level":3,"score":0.2874999940395355},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2549999952316284},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02760","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.02760","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02760","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"large":[1],"language":[2],"models":[3],"(dLLMs)":[4],"have":[5],"recently":[6],"attracted":[7],"significant":[8],"attention":[9],"for":[10,32,49],"their":[11,20],"ability":[12],"to":[13],"enhance":[14],"diversity,":[15],"controllability,":[16],"and":[17,76,89,120,132,144,154],"parallelism.":[18],"However,":[19],"non-sequential,":[21],"bidirectionally":[22],"masked":[23],"generation":[24,101,156],"makes":[25],"quality":[26,78],"assessment":[27,79],"difficult,":[28],"underscoring":[29],"the":[30,56,60,63,68,106,111,122,127,159,162],"need":[31],"effective":[33,44],"self-evaluation.":[34],"In":[35],"this":[36],"work,":[37],"we":[38,96],"propose":[39],"DiSE,":[40,95],"a":[41,99],"simple":[42],"yet":[43],"self-evaluation":[45],"confidence":[46,53],"quantification":[47],"method":[48,72],"dLLMs.":[50],"DiSE":[51,125,136],"quantifies":[52],"by":[54,80],"computing":[55],"probability":[57],"of":[58,114,124,129,161],"regenerating":[59],"tokens":[61],"in":[62],"entire":[64],"generated":[65],"sequence,":[66],"given":[67],"full":[69],"context.":[70],"This":[71],"enables":[73],"more":[74],"efficient":[75],"reliable":[77],"leveraging":[81],"token":[82],"regeneration":[83],"probabilities,":[84],"facilitating":[85],"both":[86,141],"likelihood":[87,150],"estimation":[88],"robust":[90],"uncertainty":[91,152],"quantification.":[92],"Building":[93],"upon":[94],"further":[97,157],"introduce":[98],"flexible-length":[100,155],"framework,":[102],"which":[103],"adaptively":[104],"controls":[105],"sequence":[107],"length":[108],"based":[109],"on":[110,149],"model's":[112],"self-assessment":[113],"its":[115],"own":[116],"output.":[117],"We":[118],"analyze":[119],"validate":[121],"feasibility":[123],"from":[126],"perspective":[128],"dLLM":[130],"generalization,":[131],"empirically":[133],"demonstrate":[134],"that":[135],"is":[137],"positively":[138],"correlated":[139],"with":[140],"semantic":[142],"coherence":[143],"answer":[145],"accuracy.":[146],"Extensive":[147],"experiments":[148],"evaluation,":[151],"quantification,":[153],"confirm":[158],"effectiveness":[160],"proposed":[163],"DiSE.":[164]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-05T00:00:00"}