{"id":"https://openalex.org/W7166887580","doi":"https://doi.org/10.18653/v1/2026.acl-long.188","title":"Adam\u2019s Law: Textual Frequency Law on Large Language Models","display_name":"Adam\u2019s Law: Textual Frequency Law on Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166887580","doi":"https://doi.org/10.18653/v1/2026.acl-long.188"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.188","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.188","pdf_url":"https://aclanthology.org/2026.acl-long.188.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.188.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139806329","display_name":"Hongyuan Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongyuan Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139768938","display_name":"Zixuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zixuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139719083","display_name":"Zefan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zefan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078965698","display_name":"Bowen Cao","orcid":"https://orcid.org/0000-0002-4272-2381"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bowen Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139728123","display_name":"Wai Lam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wai Lam","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":0.87594425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4079","last_page":"4105"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12380","display_name":"Authorship Attribution and Profiling","score":0.48100000619888306,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.48100000619888306,"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":0.06679999828338623,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.061400000005960464,"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/natural-language","display_name":"Natural language","score":0.3864000141620636},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3467000126838684},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.288100004196167},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2847999930381775},{"id":"https://openalex.org/keywords/language-identification","display_name":"Language identification","score":0.2660999894142151}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5891000032424927},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5062000155448914},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45410001277923584},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4311999976634979},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3864000141620636},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2847999930381775},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.188","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.188","pdf_url":"https://aclanthology.org/2026.acl-long.188.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.188","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.188","pdf_url":"https://aclanthology.org/2026.acl-long.188.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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166887580.pdf","grobid_xml":"https://content.openalex.org/works/W7166887580.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"textual":[1,32,63,106],"frequency":[2],"has":[3],"been":[4],"validated":[5],"as":[6],"relevant":[7],"to":[8,16,40,88,98,117,135],"human":[9],"cognition":[10],"in":[11,29,79,126,150],"reading":[12],"speed,":[13],"its":[14],"relatedness":[15],"Large":[17],"Language":[18],"Models":[19],"(LLMs)":[20],"is":[21,36,47],"seldom":[22],"studied.We":[23],"propose":[24,84,109,141],"a":[25,103],"novel":[26],"research":[27],"direction":[28],"terms":[30],"of":[31,43,49,154,182],"data":[33,64],"frequency,":[34],"which":[35,59],"an":[37,95,151],"understudied":[38],"topic,":[39],"the":[41,90,100,124,127,130,137,180],"best":[42],"our":[44,160,183],"knowledge.Our":[45],"framework":[46],"composed":[48],"three":[50],"units.First,":[51],"this":[52],"paper":[53],"proposes":[54],"Textual":[55,110,143,163],"Frequency":[56,111,144,164],"Law":[57],"(TFL),":[58],"indicates":[60],"that":[61,147],"frequent":[62,105],"should":[65],"be":[66],"preferred":[67],"for":[68,70],"LLMs":[69,76,116,149],"both":[71],"prompting":[72],"and":[73,129,175],"fine-tuning.Since":[74],"many":[75],"are":[77,133,157],"closedsource":[78],"their":[80],"training":[81],"data,":[82],"we":[83,108,140],"using":[85],"online":[86],"resources":[87],"estimate":[89],"sentencelevel":[91,155],"frequency.We":[92],"then":[93],"utilize":[94],"input":[96,101],"paraphraser":[97],"paraphrase":[99],"into":[102],"more":[104],"expression.Next,":[107],"Distillation":[112],"(TFD)":[113],"by":[114,121],"querying":[115],"conduct":[118],"story":[119],"completion":[120],"further":[122],"extending":[123],"sentences":[125],"datasets,":[128],"resulting":[131],"corpora":[132],"used":[134],"adjust":[136],"initial":[138],"estimation.Finally,":[139],"Curriculum":[142],"Training":[145],"(CTFT)":[146],"finetunes":[148],"increasing":[152],"order":[153],"frequency.Experiments":[156],"conducted":[158],"on":[159,168],"curated":[161],"dataset":[162],"Paired":[165],"Dataset":[166],"(TFPD)":[167],"math":[169],"reasoning,":[170],"machine":[171],"translation,":[172],"commonsense":[173],"reasoning":[174],"agentic":[176],"tool":[177],"calling.Results":[178],"show":[179],"effectiveness":[181],"framework.":[184]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}