{"id":"https://openalex.org/W4412887703","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1111","title":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","display_name":"The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412887703","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1111"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1111","pdf_url":"https://aclanthology.org/2025.findings-acl.1111.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.1111.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106342743","display_name":"Yihuai Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihuai Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114091366","display_name":"Meng Cao","orcid":"https://orcid.org/0009-0008-7414-0838"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Meng Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101774348","display_name":"Dian Zhou","orcid":"https://orcid.org/0000-0003-0902-5370"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dian Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101475928","display_name":"Yu Lei","orcid":"https://orcid.org/0000-0003-2477-3377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5001708146","display_name":"Zhijing Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhijing Jin","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":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21565","last_page":"21585"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.983299970626831,"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/T12031","display_name":"Speech and dialogue systems","score":0.983299970626831,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9433000087738037,"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":0.9106000065803528,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/memorization","display_name":"Memorization","score":0.7602752447128296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6411988139152527},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4162681996822357},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.41136419773101807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33543142676353455},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2955159544944763},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.2950100898742676}],"concepts":[{"id":"https://openalex.org/C30038468","wikidata":"https://www.wikidata.org/wiki/Q4354775","display_name":"Memorization","level":2,"score":0.7602752447128296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6411988139152527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4162681996822357},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.41136419773101807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33543142676353455},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2955159544944763},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2950100898742676}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1111","pdf_url":"https://aclanthology.org/2025.findings-acl.1111.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.1111","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1111","pdf_url":"https://aclanthology.org/2025.findings-acl.1111.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":[],"awards":[{"id":"https://openalex.org/G1825186927","display_name":null,"funder_award_id":"01IS18039B","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G4980694453","display_name":null,"funder_award_id":"FKZ: 01IS18039B","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412887703.pdf","grobid_xml":"https://content.openalex.org/works/W4412887703.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/W3093895509","https://openalex.org/W3163481960","https://openalex.org/W2323394100","https://openalex.org/W280704926","https://openalex.org/W2476068070","https://openalex.org/W4323971310","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"excel":[4],"on":[5,27,99],"a":[6,51,60],"variety":[7],"of":[8,54,62,132,145],"reasoning":[9,39,76,84,100,108,133],"benchmarks,":[10],"but":[11,89],"previous":[12],"studies":[13],"suggest":[14],"they":[15],"sometimes":[16],"struggle":[17],"to":[18,20,25,94],"generalize":[19],"unseen":[21],"questions,":[22],"potentially":[23],"due":[24],"over-reliance":[26],"memorized":[28],"training":[29],"examples.However,":[30],"the":[31,66,72,111,116,129,140,143],"precise":[32],"conditions":[33],"under":[34],"which":[35],"LLMs":[36,137],"switch":[37],"between":[38,74],"and":[40,77,134,138,148,154],"memorization":[41],"during":[42,121],"text":[43],"generation":[44],"remain":[45],"unclear.In":[46],"this":[47],"work,":[48],"we":[49,102],"provide":[50],"mechanistic":[52],"understanding":[53],"LLMs'":[55],"reasoning-memorization":[56],"dynamics":[57],"by":[58],"identifying":[59],"set":[61],"linear":[63],"features":[64,80,109],"in":[65,106,136],"model's":[67],"residual":[68],"stream":[69],"that":[70,104],"govern":[71],"balance":[73],"genuine":[75],"memory":[78,135],"recall.These":[79],"not":[81],"only":[82],"distinguish":[83],"tasks":[85],"from":[86],"memory-intensive":[87],"ones":[88],"can":[90],"also":[91],"be":[92],"manipulated":[93],"causally":[95],"influence":[96],"model":[97,112],"performance":[98],"tasks.Additionally,":[101],"show":[103],"intervening":[105],"these":[107],"helps":[110],"more":[113,146],"accurately":[114],"activate":[115],"most":[117],"relevant":[118],"problemsolving":[119],"capabilities":[120],"answer":[122],"generation.Our":[123],"findings":[124],"offer":[125],"new":[126],"insights":[127],"into":[128],"underlying":[130],"mechanisms":[131],"pave":[139],"way":[141],"for":[142],"development":[144],"robust":[147],"interpretable":[149],"generative":[150],"AI":[151],"systems.Our":[152],"code":[153],"data":[155],"are":[156],"at":[157],"https://github.com/yihuaihong/":[158],"Linear_Reasoning_Memory_Features.":[159]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}