{"id":"https://openalex.org/W4412889784","doi":"https://doi.org/10.18653/v1/2025.acl-long.1396","title":"Length-Induced Embedding Collapse in PLM-based Models","display_name":"Length-Induced Embedding Collapse in PLM-based Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889784","doi":"https://doi.org/10.18653/v1/2025.acl-long.1396"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1396","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1396","pdf_url":"https://aclanthology.org/2025.acl-long.1396.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.1396.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104214454","display_name":"Yuqi Zhou","orcid":"https://orcid.org/0009-0009-5656-8475"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqi Zhou","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075518954","display_name":"Sunhao Dai","orcid":"https://orcid.org/0009-0002-7549-0860"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sunhao Dai","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086938532","display_name":"Zhenhua Cao","orcid":"https://orcid.org/0000-0002-5247-8896"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanshuo Cao","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100696226","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0003-0824-9284"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020766468","display_name":"Jun Xu","orcid":"https://orcid.org/0000-0001-7170-111X"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China , Beijing , China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28767","last_page":"28791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12405","display_name":"Characterization and Applications of Magnetic Nanoparticles","score":0.5697000026702881,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12405","display_name":"Characterization and Applications of Magnetic Nanoparticles","score":0.5697000026702881,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6752241849899292},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4616137742996216},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1618809998035431}],"concepts":[{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6752241849899292},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4616137742996216},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1618809998035431}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1396","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1396","pdf_url":"https://aclanthology.org/2025.acl-long.1396.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1396","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1396","pdf_url":"https://aclanthology.org/2025.acl-long.1396.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":[{"score":0.6800000071525574,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[{"id":"https://openalex.org/G1840373507","display_name":null,"funder_award_id":"62376275","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322499","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92"},{"id":"https://openalex.org/F4320322724","display_name":"Ministry of Education, India","ror":"https://ror.org/048xjjh50"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889784.pdf","grobid_xml":"https://content.openalex.org/works/W4412889784.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4391900009"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Text":[0],"embeddings":[1,30,46,101,123,158],"from":[2],"PLM-based":[3,85],"models":[4],"enable":[5],"a":[6,23,41,70,81,107,132],"wide":[7],"range":[8],"of":[9,31,47,74,96,122,168,188],"applications,":[10],"yet":[11],"their":[12],"performance":[13,60,166],"often":[14],"degrades":[15],"on":[16,170,174,179],"longer":[17,32,64,125],"texts.In":[18],"this":[19,128],"paper,":[20],"we":[21,25,87,130],"introduce":[22],"phenomenon":[24],"call":[26],"Length":[27,139],"Collapse,":[28],"where":[29],"texts":[33,65],"tend":[34],"to":[35,58,102,116,165],"cluster":[36],"together.This":[37],"clustering":[38,117],"results":[39],"in":[40,84,145],"distributional":[42],"inconsistency":[43],"between":[44,149],"the":[45,59,75,94,120,138,143,186],"short":[48,152],"and":[49,118,151,172],"long":[50,150],"texts.We":[51],"further":[52],"investigate":[53],"how":[54],"these":[55],"differences":[56],"contribute":[57],"decline":[61],"observed":[62],"with":[63],"across":[66,159],"various":[67],"downstream":[68],"tasks.Through":[69],"rigorous":[71],"theoretical":[72],"analysis":[73],"self-attention":[76],"mechanism,":[77],"which":[78,136,176],"acts":[79],"as":[80,90],"low-pass":[82,97,146],"filter":[83],"models,":[86],"demonstrate":[88],"that":[89],"text":[91,161],"length":[92],"increases,":[93],"strength":[95],"filtering":[98,147],"intensifies,":[99],"causing":[100],"retain":[103],"more":[104,113,156],"low-frequency":[105],"components.As":[106],"result,":[108],"input":[109],"token":[110],"features":[111],"become":[112],"similar,":[114],"leading":[115],"ultimately":[119],"collapse":[121],"for":[124,185],"texts.To":[126],"address":[127],"issue,":[129],"propose":[131],"simple":[133],"method,":[134],"TempScale,":[135],"mitigates":[137],"Collapse":[140],"phenomenon.By":[141],"narrowing":[142],"gap":[144],"rates":[148],"texts,":[153],"TempScale":[154],"ensures":[155],"consistent":[157],"different":[160],"lengths.This":[162],"approach":[163],"leads":[164],"improvements":[167],"0.94%":[169],"MTEB":[171],"1.10%":[173],"LongEmbed,":[175],"focuses":[177],"specifically":[178],"long-context":[180],"retrieval,":[181],"providing":[182],"strong":[183],"evidence":[184],"validity":[187],"our":[189],"analysis.The":[190],"source":[191],"code":[192],"is":[193],"available":[194],"at":[195],"https://github.":[196],"com/Yuqi-Zhou/Length_Collapse.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}