{"id":"https://openalex.org/W7166880156","doi":"https://doi.org/10.18653/v1/2026.acl-long.1855","title":"HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning","display_name":"HiEdit: Lifelong Model Editing with Hierarchical Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166880156","doi":"https://doi.org/10.18653/v1/2026.acl-long.1855"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1855","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1855","pdf_url":"https://aclanthology.org/2026.acl-long.1855.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.1855.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139847426","display_name":"Yangfan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yangfan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133615084","display_name":"Tianyang Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyang Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139838588","display_name":"Chen Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139741572","display_name":"Jie Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139765003","display_name":"Wei Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Cai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064238181","display_name":"Jingchi Jiang","orcid":"https://orcid.org/0000-0003-2167-4082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingchi Jiang","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":0.86836366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39924","last_page":"39942"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.09880000352859497,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.09880000352859497,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.08550000190734863,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05119999870657921,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.4731000065803528},{"id":"https://openalex.org/keywords/lifelong-learning","display_name":"Lifelong learning","score":0.3497999906539917},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.30079999566078186},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.2824000120162964},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2680000066757202},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2667999863624573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6075000166893005},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43709999322891235},{"id":"https://openalex.org/C108771440","wikidata":"https://www.wikidata.org/wiki/Q368475","display_name":"Lifelong learning","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3188000023365021},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2667999863624573},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1855","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1855","pdf_url":"https://aclanthology.org/2026.acl-long.1855.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.1855","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1855","pdf_url":"https://aclanthology.org/2026.acl-long.1855.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":[{"id":"https://openalex.org/G1393979324","display_name":null,"funder_award_id":"2025YFE0209200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G3537643952","display_name":null,"funder_award_id":"62350710797","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G432708553","display_name":null,"funder_award_id":"2024ZX01A07","funder_id":"https://openalex.org/F4320317323","funder_display_name":"Key Research and Development Program of Heilongjiang"},{"id":"https://openalex.org/G4513401911","display_name":null,"funder_award_id":"JD2023GJ01","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8886107574","display_name":null,"funder_award_id":"JD2023GJ01","funder_id":"https://openalex.org/F4320317323","funder_display_name":"Key Research and Development Program of Heilongjiang"}],"funders":[{"id":"https://openalex.org/F4320317323","display_name":"Key Research and Development Program of Heilongjiang","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166880156.pdf","grobid_xml":"https://content.openalex.org/works/W7166880156.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Lifelong":[0],"model":[1],"editing":[2,39,101],"(LME)":[3],"aims":[4],"to":[5,28],"sequentially":[6],"rectify":[7],"outdated":[8],"or":[9],"inaccurate":[10],"knowledge":[11,51,69],"in":[12,54,66,72],"deployed":[13],"LLMs":[14,122],"while":[15],"minimizing":[16],"side":[17],"effects":[18],"on":[19,120],"unrelated":[20],"inputs.However,":[21],"existing":[22],"approaches":[23],"typically":[24],"apply":[25],"parameter":[26],"perturbations":[27],"a":[29,87],"static":[30],"and":[31,70,78,108],"dense":[32],"set":[33],"of":[34,50,57,129,136,142],"LLM":[35],"layers":[36,56,98,144],"for":[37,75,99,113],"all":[38],"instances.This":[40],"practice":[41],"is":[42,148],"counter-intuitive,":[43],"as":[44],"we":[45,84],"hypothesize":[46],"that":[47,92,124],"different":[48],"pieces":[49],"are":[52],"stored":[53],"distinct":[55],"the":[58,95,127,130,143],"model.Neglecting":[59],"this":[60],"layer-wise":[61],"specificity":[62],"can":[63],"impede":[64],"adaptability":[65],"integrating":[67],"new":[68],"result":[71],"catastrophic":[73],"forgetting":[74],"both":[76],"general":[77],"previously":[79],"edited":[80],"knowledge.To":[81],"address":[82],"this,":[83],"propose":[85],"HiEdit,":[86],"hierarchical":[88],"reinforcement":[89],"learning":[90],"framework":[91],"adaptively":[93],"identifies":[94],"most":[96],"knowledge-relevant":[97],"each":[100],"instance.By":[102],"enabling":[103],"dynamic,":[104],"instance-aware":[105],"layer":[106],"selection":[107],"incorporating":[109],"an":[110,134],"intrinsic":[111],"reward":[112],"sparsity,":[114],"HiEdit":[115,125],"achieves":[116],"precise,":[117],"localized":[118],"updates.Experiments":[119],"various":[121],"show":[123],"boosts":[126],"performance":[128],"competitive":[131],"RLEdit":[132],"by":[133],"average":[135],"8.48%":[137],"with":[138],"perturbing":[139],"only":[140],"half":[141],"per":[145],"edit.Our":[146],"code":[147],"available":[149],"at:":[150],"https://github.com/yangfanww/hiedit.":[151]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}