{"id":"https://openalex.org/W4412889813","doi":"https://doi.org/10.18653/v1/2025.acl-long.1374","title":"Causal Estimation of Tokenisation Bias","display_name":"Causal Estimation of Tokenisation Bias","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889813","doi":"https://doi.org/10.18653/v1/2025.acl-long.1374"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1374","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1374","pdf_url":"https://aclanthology.org/2025.acl-long.1374.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1374.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092048136","display_name":"Pietro Lesci","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Pietro Lesci","raw_affiliation_strings":["University of Cambridge ETH Zrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge ETH Zrich","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029033876","display_name":"Clara Meister","orcid":"https://orcid.org/0000-0002-3775-4426"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Clara Meister","raw_affiliation_strings":["University of Cambridge ETH Zrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge ETH Zrich","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045413165","display_name":"Thomas Hofmann","orcid":"https://orcid.org/0000-0003-4057-7165"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Thomas Hofmann","raw_affiliation_strings":["University of Cambridge ETH Zrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge ETH Zrich","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067943980","display_name":"Andreas Vlachos","orcid":"https://orcid.org/0000-0003-2123-5071"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Andreas Vlachos","raw_affiliation_strings":["University of Cambridge ETH Zrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge ETH Zrich","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102825308","display_name":"Tiago Pimentel","orcid":"https://orcid.org/0000-0002-5159-4641"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]},{"id":"https://openalex.org/I4210096386","display_name":"Bridge University","ror":"https://ror.org/00cbm0437","country_code":"SS","type":"education","lineage":["https://openalex.org/I4210096386"]}],"countries":["GB","SS"],"is_corresponding":false,"raw_author_name":"Tiago Pimentel","raw_affiliation_strings":["University of Cambridge ETH Zrich"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge ETH Zrich","institution_ids":["https://openalex.org/I241749","https://openalex.org/I4210096386"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.19435216,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28325","last_page":"28340"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.38760000467300415,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.38760000467300415,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.536952018737793},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5184621214866638},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.10848650336265564}],"concepts":[{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.536952018737793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5184621214866638},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.10848650336265564},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1374","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1374","pdf_url":"https://aclanthology.org/2025.acl-long.1374.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:doi:10.17863/cam.123579","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1374","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1374","pdf_url":"https://aclanthology.org/2025.acl-long.1374.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889813.pdf","grobid_xml":"https://content.openalex.org/works/W4412889813.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Modern":[0],"language":[1,189],"models":[2],"are":[3],"typically":[4],"trained":[5,71,88],"over":[6,13],"subword":[7,60],"sequences,":[8],"but":[9],"ultimately":[10],"define":[11,37],"probabilities":[12],"character-strings.Ideally,":[14],"the":[15,18,26,30,53,68,75,107,113,122],"choice":[16,187],"of":[17,50,55],"tokeniser-which":[19],"maps":[20],"characterstrings":[21],"to":[22,29,74,125,178],"subwords-should":[23],"not":[24,58],"affect":[25],"probability":[27,69,175],"assigned":[28],"underlying":[31],"characterstring;":[32],"in":[33,63,166,188],"practice,":[34],"it":[35,105],"does.We":[36],"this":[38,43,80,94,148],"mismatch":[39],"as":[40,99,183],"tokenisation":[41,51,97,116,153,182],"bias.In":[42],"work,":[44],"we":[45,111,137,150],"quantify":[46],"one":[47,91],"particular":[48],"type":[49],"bias:":[52],"effect":[54,81,102,142],"including":[56],"or":[57],"a":[59,64,70,100,126,140,163,167,184],"(e.g.,":[61],"hello)":[62],"tokeniser's":[65,127],"vocabulary":[66,170],"on":[67],"model":[72,86],"assigns":[73],"corresponding":[76],"characters":[77],"(i.e.,":[78],"\"hello\").Estimating":[79],"is":[82,87,131],"challenging":[83],"because":[84],"each":[85],"with":[89],"only":[90],"tokeniser.We":[92],"address":[93],"by":[95,143,176],"framing":[96],"bias":[98],"causal":[101,141],"and":[103,120,161],"estimating":[104],"using":[106],"regression":[108],"discontinuity":[109],"design.Specifically,":[110],"exploit":[112],"fact":[114],"that":[115,152],"algorithms":[117],"rank":[118],"subwords":[119,146],"add":[121],"first":[123],"K":[124,130],"vocabulary,":[128],"where":[129],"an":[132],"arbitrary":[133],"cutoff":[134],"point.As":[135],"such,":[136],"can":[138],"estimate":[139],"comparing":[144],"similar":[145],"around":[147],"cutoff.Experimentally,":[149],"find":[151],"consistently":[154],"affects":[155],"models'":[156],"outputs":[157],"across":[158],"scales,":[159],"vocabularies,":[160],"tokenisers.Notably,":[162],"subword's":[164],"presence":[165],"small":[168],"model's":[169],"may":[171],"increase":[172],"its":[173],"characters'":[174],"up":[177],"17":[179],"times,":[180],"highlighting":[181],"key":[185],"design":[186],"modelling.":[190]},"counts_by_year":[],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}