{"id":"https://openalex.org/W4417469573","doi":"https://doi.org/10.18653/v1/2026.gem-main.5","title":"Temporal Tokenization Strategies for Event Sequence Modeling with Large Language Models","display_name":"Temporal Tokenization Strategies for Event Sequence Modeling with Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417469573","doi":"https://doi.org/10.18653/v1/2026.gem-main.5"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.gem-main.5","doi":"https://doi.org/10.18653/v1/2026.gem-main.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.gem-main.5","pdf_url":"https://aclanthology.org/2026.gem-main.5.pdf","source":{"id":"https://openalex.org/S7407106858","display_name":"Workshop on Generation, Evaluation and Metrics (GEM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.gem-main.5.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026087229","display_name":"Zefang Liu","orcid":"https://orcid.org/0000-0003-1947-3249","observed_orcids":["https://orcid.org/0000-0003-1947-3249"]},"institutions":[{"id":"https://openalex.org/I1305444813","display_name":"Capital One (United States)","ror":"https://ror.org/00svp7168","country_code":"US","type":"company","lineage":["https://openalex.org/I1305444813"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zefang Liu","raw_affiliation_strings":["Capital One , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Capital One , USA","institution_ids":["https://openalex.org/I1305444813"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103324660","display_name":"Nam H. Nguyen","orcid":"https://orcid.org/0009-0008-6981-4463","observed_orcids":["https://orcid.org/0009-0008-6981-4463","https://orcid.org/0000-0002-1254-0069"]},"institutions":[{"id":"https://openalex.org/I1305444813","display_name":"Capital One (United States)","ror":"https://ror.org/00svp7168","country_code":"US","type":"company","lineage":["https://openalex.org/I1305444813"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nam H Nguyen","raw_affiliation_strings":["Capital One , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Capital One , USA","institution_ids":["https://openalex.org/I1305444813"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073432713","display_name":"Yinzhu Quan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinzhu Quan","raw_affiliation_strings":["Georgia Institute of Technology , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology , USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056567731","display_name":"Shixiong Zhang","orcid":"https://orcid.org/0000-0002-0314-9199","observed_orcids":["https://orcid.org/0000-0002-0314-9199","https://orcid.org/0000-0002-3816-839X"]},"institutions":[{"id":"https://openalex.org/I1305444813","display_name":"Capital One (United States)","ror":"https://ror.org/00svp7168","country_code":"US","type":"company","lineage":["https://openalex.org/I1305444813"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi-Xiong Zhang","raw_affiliation_strings":["Capital One , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Capital One , USA","institution_ids":["https://openalex.org/I1305444813"]}]}],"institutions":[],"countries_distinct_count":1,"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":0.02570977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41","last_page":"51"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6557999849319458,"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":0.6557999849319458,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.2761000096797943,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T13702","display_name":"Machine Learning in Healthcare","score":0.01769999973475933,"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/event-sequence-modeling","display_name":"event sequence modeling","score":0.7269999980926514},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9179999828338623},{"id":"https://openalex.org/keywords/scalar-quantization","display_name":"scalar quantization","score":0.7379999756813049},{"id":"https://openalex.org/keywords/time-encoding","display_name":"time encoding","score":0.4869999885559082},{"id":"https://openalex.org/keywords/llm-fine-tuning","display_name":"LLM fine-tuning","score":0.722000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.762499988079071},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6468999981880188},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.5737000107765198},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5070000290870667},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4973999857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49219998717308044},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48019999265670776},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.36809998750686646},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C57691317","wikidata":"https://www.wikidata.org/wiki/Q1289248","display_name":"Scalar (mathematics)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29989999532699585},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.26510000228881836},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.gem-main.5","doi":"https://doi.org/10.18653/v1/2026.gem-main.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.gem-main.5","pdf_url":"https://aclanthology.org/2026.gem-main.5.pdf","source":{"id":"https://openalex.org/S7407106858","display_name":"Workshop on Generation, Evaluation and Metrics (GEM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.13618","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2512.13618","pdf_url":"https://arxiv.org/pdf/2512.13618","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,"listed_in":[],"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.2512.13618","doi":"https://doi.org/10.48550/arxiv.2512.13618","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.13618","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.gem-main.5","doi":"https://doi.org/10.18653/v1/2026.gem-main.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.gem-main.5","pdf_url":"https://aclanthology.org/2026.gem-main.5.pdf","source":{"id":"https://openalex.org/S7407106858","display_name":"Workshop on Generation, Evaluation and Metrics (GEM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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 Fifth Workshop on Generation, Evaluation and Metrics (GEM)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417469573.pdf","grobid_xml":"https://content.openalex.org/works/W4417469573.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4400266577","https://openalex.org/W4417360275","https://openalex.org/W4403863493","https://openalex.org/W7204494917","https://openalex.org/W7138125736","https://openalex.org/W7118853862","https://openalex.org/W7214082371","https://openalex.org/W4407424207","https://openalex.org/W4401662125","https://openalex.org/W7162793318"],"abstract_inverted_index":{"Representing":[0],"continuous":[1],"time":[2],"is":[3,109],"a":[4,55,130],"critical":[5,131],"and":[6,84],"under-explored":[7],"challenge":[8],"in":[9,137],"modeling":[10,63],"temporal":[11,60,127],"event":[12,42,64,139],"sequences":[13,65],"with":[14,66,121],"large":[15],"language":[16],"models":[17],"(LLMs).Various":[18],"strategies":[19,91],"like":[20],"byte-level":[21,76],"representations":[22],"or":[23],"calendar":[24,79],"tokens":[25],"have":[26],"been":[27],"proposed.However,":[28],"the":[29,36,119,122],"optimal":[30],"approach":[31],"remains":[32],"unclear,":[33],"especially":[34],"given":[35],"diverse":[37,101],"statistical":[38,124],"distributions":[39],"of":[40,59],"real-world":[41,96],"data,":[43],"which":[44],"range":[45],"from":[46],"smooth":[47],"log-normal":[48],"to":[49],"discrete,":[50],"spiky":[51],"patterns.This":[52],"paper":[53],"presents":[54],"systematic":[56],"empirical":[57],"study":[58],"tokenization":[61,128],"for":[62],"LLMs,":[67],"comparing":[68],"distinct":[69],"encoding":[70],"strategies:":[71],"naive":[72],"numeric":[73],"strings,":[74],"high-precision":[75],"representations,":[77],"human-semantic":[78],"tokens,":[80],"classic":[81],"uniform":[82],"binning,":[83],"adaptive":[85],"residual":[86],"scalar":[87],"quantization.We":[88],"evaluate":[89],"these":[90,100],"by":[92],"fine-tuning":[93],"LLMs":[94],"on":[95,117],"datasets":[97],"that":[98,105],"exemplify":[99],"distributions.Our":[102],"analysis":[103],"reveals":[104],"no":[106],"single":[107],"strategy":[108],"universally":[110],"superior;":[111],"instead,":[112],"prediction":[113],"performance":[114],"depends":[115],"heavily":[116],"aligning":[118],"tokenizer":[120],"data's":[123],"properties,":[125],"highlighting":[126],"as":[129],"yet":[132],"often":[133],"overlooked":[134],"design":[135],"dimension":[136],"LLM-based":[138],"modeling.":[140]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-12-17T00:00:00"}