{"id":"https://openalex.org/W7164156227","doi":"https://doi.org/10.48550/arxiv.2606.10199","title":"A Continuous-Time Markov Chain Framework for Insertion Language Models","display_name":"A Continuous-Time Markov Chain Framework for Insertion Language Models","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164156227","doi":"https://doi.org/10.48550/arxiv.2606.10199"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.10199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.10199","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138292884","display_name":"Dhruvesh Patel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patel, Dhruvesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083642776","display_name":"Benjamin Rozonoyer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rozonoyer, Benjamin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103216448","display_name":"Soumitra Das","orcid":"https://orcid.org/0000-0001-8341-7474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Das, Soumitra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043295314","display_name":"Tahira Naseem","orcid":"https://orcid.org/0009-0009-0603-2760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naseem, Tahira","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031809940","display_name":"Tim G. J. Rudner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rudner, Tim G. J.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138331409","display_name":"Andrew McCallum","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McCallum, Andrew","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/T10181","display_name":"Natural Language Processing Techniques","score":0.43700000643730164,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.43700000643730164,"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":0.1678999960422516,"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":0.14110000431537628,"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/markov-chain","display_name":"Markov chain","score":0.6988000273704529},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5856999754905701},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4749999940395355},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4253999888896942},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4242999851703644},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.4189999997615814},{"id":"https://openalex.org/keywords/chain","display_name":"Chain (unit)","score":0.40290001034736633},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3801000118255615}],"concepts":[{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.6988000273704529},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6690999865531921},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5856999754905701},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4749999940395355},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.4189999997615814},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.415800005197525},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3801000118255615},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.36010000109672546},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3402999937534332},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.32820001244544983},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2815000116825104},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2685999870300293},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.10199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.10199","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.10199","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Insertion":[0],"Language":[1],"Models":[2],"(ILMs)":[3],"offer":[4],"several":[5],"advantages":[6],"over":[7,90],"left-to-right":[8,91,106],"generation":[9,18,89,92,107],"and":[10,93,108],"mask-based":[11],"generation.":[12],"However,":[13],"existing":[14,120],"formulations":[15,57],"of":[16,50,58,66,87],"insertion-based":[17,88],"have":[19],"largely":[20],"been":[21],"ad-hoc.":[22],"In":[23,97],"this":[24,67],"paper,":[25],"we":[26,78],"derive":[27],"a":[28,43,74],"diffusion-style":[29],"denoising":[30,68],"objective":[31],"for":[32],"ILMs":[33,59],"from":[34],"first":[35],"principles":[36],"by":[37],"formulating":[38],"the":[39,48,81,85],"noising":[40],"process":[41],"as":[42,63],"continuous-time":[44],"Markov":[45],"chain":[46],"on":[47,73],"space":[49],"variable-length":[51],"sequences.":[52],"We":[53],"show":[54,79],"that":[55,80],"previous":[56],"can":[60],"be":[61],"viewed":[62],"special":[64],"cases":[65],"framework.":[69],"Through":[70],"empirical":[71],"evaluation":[72],"synthetic":[75],"planning":[76],"task,":[77],"proposed":[82],"approach":[83,102],"retains":[84],"benefits":[86],"masked":[94,109],"diffusion":[95,110],"models.":[96,123],"language":[98,122],"modeling,":[99],"our":[100],"diffusion-based":[101],"is":[103],"competitive":[104],"with":[105],"models,":[111],"while":[112],"offering":[113],"additional":[114],"flexibility":[115],"in":[116],"sampling":[117],"compared":[118],"to":[119],"insertion":[121]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-11T00:00:00"}