{"id":"https://openalex.org/W7166808471","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1322","title":"Will it Merge? On The Causes of Model Mergeability","display_name":"Will it Merge? On The Causes of Model Mergeability","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166808471","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1322"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1322","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1322","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1322","pdf_url":"https://aclanthology.org/2026.findings-acl.1322.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.1322.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012548597","display_name":"Adir Rahamim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Adir Rahamim","raw_affiliation_strings":["Technion -Israel Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technion -Israel Institute of Technology ,","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024163531","display_name":"Asaf Yehudai","orcid":"https://orcid.org/0000-0002-3743-7551","observed_orcids":["https://orcid.org/0000-0002-3743-7551"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I197251160","display_name":"Hebrew University of Jerusalem","ror":"https://ror.org/03qxff017","country_code":"IL","type":"education","lineage":["https://openalex.org/I197251160"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Asaf Yehudai","raw_affiliation_strings":["Hebrew University of Jerusalem ,","IBM Research AI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hebrew University of Jerusalem ,","institution_ids":["https://openalex.org/I197251160"]},{"raw_affiliation_string":"IBM Research AI ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016326349","display_name":"Boaz Carmeli","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Boaz Carmeli","raw_affiliation_strings":["IBM Research AI ,","Technion -Israel Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI ,","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"Technion -Israel Institute of Technology ,","institution_ids":["https://openalex.org/I174306211"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040286212","display_name":"Leshem Choshen","orcid":"https://orcid.org/0000-0002-0085-6496","observed_orcids":["https://orcid.org/0000-0002-0085-6496"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leshem Choshen","raw_affiliation_strings":["MIT ,","MIT-IBM Watson AI Lab ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT ,","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"MIT-IBM Watson AI Lab ,","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080909766","display_name":"Yosi Mass","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yosi Mass","raw_affiliation_strings":["IBM Research AI ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051184573","display_name":"Yonatan Belinkov","orcid":"https://orcid.org/0000-0002-6280-5045","observed_orcids":["https://orcid.org/0000-0002-6280-5045"]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]},{"id":"https://openalex.org/I174306211","display_name":"Technion \u2013 Israel Institute of Technology","ror":"https://ror.org/03qryx823","country_code":"IL","type":"education","lineage":["https://openalex.org/I174306211"]}],"countries":["IL","US"],"is_corresponding":false,"raw_author_name":"Yonatan Belinkov","raw_affiliation_strings":["Kempner Institute , Harvard University","Technion -Israel Institute of Technology ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kempner Institute , Harvard University","institution_ids":["https://openalex.org/I136199984"]},{"raw_affiliation_string":"Technion -Israel Institute of Technology ,","institution_ids":["https://openalex.org/I174306211"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.44113262,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26551","last_page":"26570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9589999914169312,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9589999914169312,"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":0.029100000858306885,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00570000009611249,"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/model-merging","display_name":"model merging","score":0.9620000123977661},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"multi-task learning","score":0.6510000228881836},{"id":"https://openalex.org/keywords/fine-tuned-models","display_name":"fine-tuned models","score":0.7649999856948853},{"id":"https://openalex.org/keywords/knowledge-preservation","display_name":"knowledge preservation","score":0.7379999756813049},{"id":"https://openalex.org/keywords/transfer-learning","display_name":"transfer learning","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8183000087738037},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.5878999829292297},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48089998960494995},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.45809999108314514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2565000057220459}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1322","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1322","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1322","pdf_url":"https://aclanthology.org/2026.findings-acl.1322.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1322","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1322","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1322","pdf_url":"https://aclanthology.org/2026.findings-acl.1322.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320315389","display_name":"Open Philanthropy Project","ror":"https://ror.org/004d1k391"},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320323139","display_name":"Azrieli Foundation","ror":"https://ror.org/009svts64"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166808471.pdf","grobid_xml":"https://content.openalex.org/works/W7166808471.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7127126510","https://openalex.org/W7117306415","https://openalex.org/W4409992742","https://openalex.org/W4415797037","https://openalex.org/W6979296337","https://openalex.org/W4416034030","https://openalex.org/W7214055981","https://openalex.org/W7134957813","https://openalex.org/W6966851397","https://openalex.org/W4402670690"],"abstract_inverted_index":{"Model":[0],"merging":[1,25,106],"has":[2],"emerged":[3],"as":[4,69],"a":[5,14,49,70,103],"promising":[6],"technique":[7,107],"for":[8,59],"combining":[9],"multiple":[10],"fine-tuned":[11],"models":[12,39,87],"into":[13],"single":[15],"multitask":[16],"model":[17,67,80,94],"without":[18],"retraining.However,":[19],"the":[20,65,78,92,114],"factors":[21],"that":[22,77,91,108],"determine":[23],"whether":[24],"will":[26],"succeed":[27],"or":[28,61],"fail":[29],"remain":[30],"poorly":[31],"understood.In":[32],"this":[33],"work,":[34],"we":[35,47,101],"investigate":[36,55],"why":[37],"specific":[38],"are":[40,83],"merged":[41],"better":[42,82,109],"than":[43,86],"others.To":[44],"do":[45],"so,":[46],"propose":[48],"concrete,":[50],"measurable":[51],"definition":[52],"of":[53],"mergeability.We":[54],"several":[56],"potential":[57],"causes":[58],"high":[60],"low":[62],"mergeability,":[63],"highlighting":[64],"base":[66,79,93,115],"knowledge":[68,112],"dominant":[71],"factor:":[72],"Models":[73],"finetuned":[74,88],"on":[75,89,97],"instances":[76,90],"knows":[81],"more":[84],"mergeable":[85],"struggles":[95],"with.Based":[96],"our":[98],"mergeability":[99],"definition,":[100],"explore":[102],"simple":[104],"weighted":[105],"preserves":[110],"weak":[111],"in":[113],"model.":[116]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}
