{"id":"https://openalex.org/W4416435606","doi":"https://doi.org/10.18653/v1/2026.acl-long.63","title":"PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise","display_name":"PrefixNLI: Detecting Factual Inconsistencies as Soon as They Arise","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416435606","doi":"https://doi.org/10.18653/v1/2026.acl-long.63"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.63","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.63","pdf_url":"https://aclanthology.org/2026.acl-long.63.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.63.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Sapir Harary","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sapir Harary","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031847181","display_name":"Eran Hirsch","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eran Hirsch","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091218611","display_name":"Aviv Slobodkin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aviv Slobodkin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059607973","display_name":"David Wan","orcid":"https://orcid.org/0000-0001-9361-8245"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Wan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001987532","display_name":"Mohit Bansal","orcid":"https://orcid.org/0000-0001-5522-1351"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohit Bansal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033006575","display_name":"Ido Dagan","orcid":"https://orcid.org/0000-0003-3415-3374"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ido Dagan","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02689628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1414","last_page":"1433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6834999918937683,"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":0.6834999918937683,"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":0.1770000010728836,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.053700000047683716,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6406000256538391},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6208999752998352},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6089000105857849},{"id":"https://openalex.org/keywords/textual-entailment","display_name":"Textual entailment","score":0.4869000017642975},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4700999855995178},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.44609999656677246},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4154999852180481},{"id":"https://openalex.org/keywords/logical-consequence","display_name":"Logical consequence","score":0.4138000011444092},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4016000032424927}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8011999726295471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6514999866485596},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6406000256538391},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6208999752998352},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6089000105857849},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5716999769210815},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.4869000017642975},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.44609999656677246},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4410000145435333},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C134752490","wikidata":"https://www.wikidata.org/wiki/Q374182","display_name":"Logical consequence","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4016000032424927},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4007999897003174},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.37630000710487366},{"id":"https://openalex.org/C2985684807","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Text generation","level":2,"score":0.3727000057697296},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3463999927043915},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2904999852180481},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2818000018596649},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2782999873161316},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.27149999141693115},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.63","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.63","pdf_url":"https://aclanthology.org/2026.acl-long.63.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.01359","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.01359","pdf_url":"https://arxiv.org/pdf/2511.01359","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.01359","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.01359","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:10.18653/v1/2026.acl-long.63","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.63","pdf_url":"https://aclanthology.org/2026.acl-long.63.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G572880119","display_name":"CAREER: Semantic Multi-Task Learning for Generalizable and Interpretable Language Generation","funder_award_id":"1846185","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G580734012","display_name":"AI Institute for Engaged Learning","funder_award_id":"2112635","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416435606.pdf","grobid_xml":"https://content.openalex.org/works/W4416435606.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Natural":[0],"Language":[1],"Inference":[2],"(NLI)":[3],"models":[4,55,130],"have":[5],"been":[6],"used":[7],"in":[8,66,135,152],"various":[9],"ways":[10],"to":[11,26,58,89],"improve":[12],"the":[13,29,35,67,85,159,164,168,176],"factuality":[14],"of":[15,163],"LLM":[16],"outputs.This":[17],"is":[18,32],"typically":[19],"done":[20],"by":[21,131,156],"applying":[22],"an":[23],"NLI":[24,54,129],"model":[25,30,117,166,170],"judge":[27],"whether":[28],"output":[31],"entailed":[33],"from":[34,167],"supposed":[36],"evidence,":[37],"triggering":[38],"some":[39],"corrective":[40],"actions,":[41],"such":[42],"as":[43],"beam":[44],"reranking":[45],"at":[46],"inference":[47],"time":[48],"or":[49],"RL":[50],"rewards":[51],"during":[52,79],"training.While":[53],"are":[56,72],"trained":[57],"detect":[59],"factual":[60,121,150],"inconsistencies":[61,122],"over":[62,91,123],"complete":[63],"sentences,":[64],"decisions":[65],"common":[68],"autoregressive":[69],"generation":[70,101],"architecture":[71],"made":[73],"for":[74,99,108],"each":[75],"evolving":[76],"text":[77,93,124],"prefix,":[78],"decoding.Addressing":[80],"this":[81,109],"setting,":[82],"we":[83,111],"generalize":[84],"entailment":[86],"detection":[87],"task":[88],"apply":[90],"arbitrary":[92],"prefixes,":[94,125],"and":[95,105,161],"suggest":[96],"its":[97],"utility":[98],"improving":[100],"faithfulness.Providing":[102],"suitable":[103],"evaluation":[104],"training":[106],"datasets":[107],"task,":[110],"train":[112],"MiniTruePrefixes,":[113],"a":[114,144],"novel":[115],"specialized":[116],"that":[118,140],"better":[119],"detects":[120],"outperforming":[126],"comparable":[127],"baseline":[128],"5-14":[132],"F1":[133],"points":[134],"prefix-level":[136],"entailment.We":[137],"further":[138],"demonstrate":[139],"integrating":[141],"MiniTruePrefixes":[142],"into":[143],"controlled":[145],"decoding":[146],"framework":[147],"substantially":[148],"improves":[149],"consistency":[151],"abstractive":[153],"summarization.When":[154],"guided":[155],"Mini-TruePrefixes,":[157],"LLaMA-3.2-3B-Instructmatches":[158],"faithfulness":[160],"runtime":[162],"8B":[165],"same":[169],"family,":[171],"while":[172],"using":[173],"only":[174],"half":[175],"memory.":[177]},"counts_by_year":[],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-11-06T00:00:00"}