{"id":"https://openalex.org/W7166876209","doi":"https://doi.org/10.18653/v1/2026.acl-long.634","title":"How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them","display_name":"How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166876209","doi":"https://doi.org/10.18653/v1/2026.acl-long.634"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.634","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.634","pdf_url":"https://aclanthology.org/2026.acl-long.634.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.634.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132697773","display_name":"Disen Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Disen Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139802481","display_name":"Freda Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Freda Shi","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":0.86450686,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13921","last_page":"13938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.19370000064373016,"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":0.19370000064373016,"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/T12090","display_name":"Language and cultural evolution","score":0.11110000312328339,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.07859999686479568,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4896000027656555},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.4309999942779541},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3950999975204468},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.34950000047683716},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.29829999804496765},{"id":"https://openalex.org/keywords/bigram","display_name":"Bigram","score":0.2912999987602234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289999723434448},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6353999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.586899995803833},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4896000027656555},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4066999852657318},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.29829999804496765},{"id":"https://openalex.org/C108757681","wikidata":"https://www.wikidata.org/wiki/Q2773912","display_name":"Bigram","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2529999911785126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.634","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.634","pdf_url":"https://aclanthology.org/2026.acl-long.634.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.634","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.634","pdf_url":"https://aclanthology.org/2026.acl-long.634.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":[{"display_name":"Quality Education","score":0.6570338010787964,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166876209.pdf","grobid_xml":"https://content.openalex.org/works/W7166876209.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tokenization":[0],"is":[1],"the":[2,14,43,61,70,77],"first":[3],"step":[4],"in":[5],"every":[6],"language":[7],"model":[8],"(LM),":[9],"yet":[10],"it":[11],"never":[12],"takes":[13],"sounds":[15],"of":[16,33,45,81],"words":[17],"into":[18,114],"account.We":[19],"investigate":[20],"how":[21],"tokenization":[22,40,75],"influences":[23],"text-only":[24],"LMs'":[25],"ability":[26],"to":[27,117],"represent":[28],"phonological":[29,54,91,112],"knowledge.Through":[30],"a":[31,66,73,94,105],"series":[32],"probing":[34],"experiments,":[35],"we":[36,59,103],"show":[37],"that":[38,68,85,110],"subword-based":[39],"systematically":[41],"weakens":[42],"encoding":[44],"both":[46],"local":[47],"(e.g.,":[48,52],"rhyme)":[49],"and":[50,76,83,128,134,139],"global":[51],"syllabification)":[53],"features.To":[55],"quantify":[56],"this":[57],"effect,":[58],"introduce":[60],"syllabification-tokenization":[62],"alignment":[63],"distance":[64],"(STAD),":[65],"metric":[67],"measures":[69],"misalignment":[71,87],"between":[72],"model's":[74],"natural":[78],"syllable":[79],"boundaries":[80],"words,":[82],"find":[84],"higher":[86],"correlates":[88],"with":[89,132],"poorer":[90],"representations,":[92],"providing":[93],"simple":[95],"diagnostic":[96],"for":[97],"phonologyaware":[98],"tokenization.To":[99],"address":[100],"these":[101],"limitations,":[102],"propose":[104],"lightweight":[106],"IPA-based":[107],"finetuning":[108],"method":[109],"infuses":[111],"awareness":[113],"LMs,":[115],"leading":[116],"consistent":[118],"improvements":[119],"across":[120],"three":[121],"phonology-related":[122],"tasks":[123],"while":[124],"largely":[125],"preserving":[126],"math":[127],"general":[129],"reasoning":[130],"ability,":[131],"1.1%":[133],"0.9%":[135],"drops":[136],"on":[137],"GSM8K":[138],"MMLU,":[140],"respectively.":[141],"1":[142]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}