{"id":"https://openalex.org/W7158960860","doi":"https://doi.org/10.48550/arxiv.2604.26209","title":"Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction","display_name":"Breaking the Autoregressive Chain: Hyper-Parallel Decoding for Efficient LLM-Based Attribute Value Extraction","publication_year":2026,"publication_date":"2026-04-29","ids":{"openalex":"https://openalex.org/W7158960860","doi":"https://doi.org/10.48550/arxiv.2604.26209"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.26209","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26209","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.2604.26209","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134904466","display_name":"Theodore Glavas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Glavas, Theodore","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080114650","display_name":"Nikhita Vedula","orcid":"https://orcid.org/0000-0003-4857-5308"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vedula, Nikhita","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007853790","display_name":"Dushyanta Dhyani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhyani, Dushyanta","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134916885","display_name":"Yilun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yilun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5059403175","display_name":"Shervin Malmasi","orcid":"https://orcid.org/0000-0001-6250-5571"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Malmasi, Shervin","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":0.2624000012874603,"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":0.2624000012874603,"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":0.16509999334812164,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.13910000026226044,"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/decoding-methods","display_name":"Decoding methods","score":0.859499990940094},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.7199000120162964},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6261000037193298},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5737000107765198},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4966000020503998},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4900999963283539},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46939998865127563}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.859499990940094},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7199000120162964},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6757000088691711},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5430999994277954},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4900999963283539},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46939998865127563},{"id":"https://openalex.org/C193969084","wikidata":"https://www.wikidata.org/wiki/Q7452500","display_name":"Sequential decoding","level":4,"score":0.4278999865055084},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.39469999074935913},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C79772020","wikidata":"https://www.wikidata.org/wiki/Q5159264","display_name":"Conditional independence","level":2,"score":0.27880001068115234},{"id":"https://openalex.org/C204397858","wikidata":"https://www.wikidata.org/wiki/Q4437907","display_name":"List decoding","level":5,"score":0.2768999934196472},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.27639999985694885},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.26209","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26209","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.2604.26209","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.26209","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":[{"display_name":"Industry, innovation and infrastructure","score":0.5757902264595032,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Some":[0],"text":[1],"generation":[2,66,89],"tasks,":[3],"such":[4],"as":[5],"Attribute":[6],"Value":[7],"Extraction":[8],"(AVE),":[9],"require":[10],"decoding":[11,23,47,52],"multiple":[12,96],"independent":[13,170],"sequences":[14,35],"from":[15],"the":[16,31,157],"same":[17],"document":[18],"context.":[19],"While":[20],"standard":[21],"autoregressive":[22],"is":[24],"slow":[25],"due":[26],"to":[27,86,108,129,156,166],"its":[28],"sequential":[29],"nature,":[30],"independence":[32],"between":[33],"output":[34,133,171],"offers":[36],"an":[37],"opportunity":[38],"for":[39,148],"parallelism.":[40],"We":[41],"present":[42],"Hyper-Parallel":[43],"Decoding,":[44],"a":[45,99],"novel":[46],"algorithm":[48],"that":[49,78],"accelerates":[50],"offline":[51],"by":[53,127],"leveraging":[54],"both":[55,120],"shared":[56],"memory":[57],"and":[58,118,123,160],"computation":[59],"across":[60],"batches.":[61],"HPD":[62,113,151],"enables":[63],"out-of-order":[64],"token":[65],"through":[67],"position":[68],"ID":[69],"manipulation,":[70],"significantly":[71],"improving":[72],"efficiency.":[73],"Experiments":[74],"on":[75,142],"AVE":[76,144,158],"show":[77],"attribute-value":[79],"pairs":[80],"are":[81],"conditionally":[82],"independent,":[83],"enabling":[84],"us":[85],"parallelize":[87],"value":[88],"within":[90,98],"each":[91],"prompt.":[92,112],"By":[93],"further":[94],"stacking":[95],"documents":[97],"single":[100],"prompt,":[101],"we":[102],"can":[103,161],"decode":[104],"in":[105,162],"parallel":[106],"up":[107,128],"96":[109],"tokens":[110],"per":[111],"works":[114],"with":[115,169],"all":[116],"LLMs,":[117],"reduces":[119],"inference":[121,125],"costs":[122],"total":[124],"time":[126],"13.8X":[130],"without":[131],"compromising":[132],"quality,":[134],"potentially":[135],"saving":[136],"hundreds":[137],"of":[138,140],"thousands":[139],"dollars":[141],"industry":[143],"tasks.":[145],"Although":[146],"designed":[147],"attribute":[149],"extraction,":[150],"makes":[152],"no":[153],"assumptions":[154],"unique":[155],"domain":[159],"theory":[163],"be":[164],"applied":[165],"other":[167],"scenarios":[168],"structures.":[172]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-01T00:00:00"}