{"id":"https://openalex.org/W4412944715","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1212","title":"Unveiling and Addressing Pseudo Forgetting in Large Language Models","display_name":"Unveiling and Addressing Pseudo Forgetting in Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944715","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1212"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1212","pdf_url":"https://aclanthology.org/2025.findings-acl.1212.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1212.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102139616","display_name":"Huashan Sun","orcid":"https://orcid.org/0000-0001-5631-1367"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huashan Sun","raw_affiliation_strings":["School of Computer Science and Technology , Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101057400","display_name":"Yizhe Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhe Yang","raw_affiliation_strings":["School of Computer Science and Technology , Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676460","display_name":"Yinghao Li","orcid":"https://orcid.org/0009-0009-3808-141X"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghao Li","raw_affiliation_strings":["School of Computer Science and Technology , Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376734","display_name":"Jiawei Li","orcid":"https://orcid.org/0000-0002-4018-0830"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiawei Li","raw_affiliation_strings":["School of Computer Science and Technology , Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["School of Computer Science and Technology , Beijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08690002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23642","last_page":"23658"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9718000292778015,"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":0.9718000292778015,"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/T10028","display_name":"Topic Modeling","score":0.946399986743927,"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/forgetting","display_name":"Forgetting","score":0.7088004946708679},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6770226955413818},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3529645800590515},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2732214629650116},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07829675078392029}],"concepts":[{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.7088004946708679},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6770226955413818},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3529645800590515},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2732214629650116},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07829675078392029}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1212","pdf_url":"https://aclanthology.org/2025.findings-acl.1212.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.1212","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1212","pdf_url":"https://aclanthology.org/2025.findings-acl.1212.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":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.5600000023841858,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G2563629645","display_name":null,"funder_award_id":"U21B2009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5603421645","display_name":null,"funder_award_id":"92370110","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/F4320335577","display_name":"Major Research Plan","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944715.pdf","grobid_xml":"https://content.openalex.org/works/W4412944715.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/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W4310285384"],"abstract_inverted_index":{"Although":[0],"substantial":[1],"efforts":[2],"have":[3],"been":[4],"made":[5],"to":[6,38,45,51,84,88,119,147],"mitigate":[7],"catastrophic":[8],"forgetting":[9,110,160],"in":[10],"continual":[11],"learning,":[12],"the":[13,24,29,46,49,53,59,85,90,98,144,150],"intrinsic":[14,151],"mechanisms":[15,100],"are":[16],"not":[17,36],"well":[18],"understood.In":[19],"this":[20,127],"work,":[21],"we":[22,104,129],"demonstrate":[23,154],"existence":[25],"of":[26,41,48,92,97,122],"\"pseudo":[27],"forgetting\":":[28],"performance":[30,61],"degradation":[31],"on":[32,62,126,143],"previous":[33,63],"tasks":[34,64],"is":[35],"attributed":[37],"a":[39],"loss":[40],"capabilities,":[42],"but":[43],"rather":[44],"failure":[47],"instructions":[50],"activate":[52],"appropriate":[54],"model":[55,163],"abilities.We":[56],"show":[57,111],"that":[58,106,137,155],"model's":[60,145],"can":[65],"be":[66],"restored":[67],"through":[68],"two":[69],"simple":[70],"interventions:":[71],"(1)":[72],"providing":[73],"partial":[74],"external":[75],"correct":[76,93],"rationale,":[77],"and":[78],"(2)":[79],"appending":[80],"semantically":[81],"meaningless":[82],"suffixes":[83],"original":[86],"instructions,":[87],"guide":[89],"generation":[91],"rationales.Through":[94],"empirical":[95],"analysis":[96],"internal":[99],"governing":[101],"rationale":[102,116],"generation,":[103,117],"reveal":[105],"models":[107],"exhibiting":[108],"pseudo":[109,159],"reduced":[112],"instruction":[113],"dependence":[114],"during":[115],"leading":[118],"suboptimal":[120],"activation":[121],"their":[123],"inherent":[124],"capabilities.Based":[125],"insight,":[128],"propose":[130],"Rationale-Guidance":[131],"Difficulty":[132],"based":[133,142],"Replay":[134],"(RGD-R)":[135],"framework":[136],"dynamically":[138],"allocates":[139],"replay":[140],"data":[141],"ability":[146],"correctly":[148],"leverage":[149],"capabilities.Experimental":[152],"results":[153],"RGD-R":[156],"effectively":[157],"mitigates":[158],"while":[161],"maintaining":[162],"plasticity.":[164]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}