{"id":"https://openalex.org/W4412944633","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1225","title":"Structured Pruning for Diverse Best-of-N Reasoning Optimization","display_name":"Structured Pruning for Diverse Best-of-N Reasoning Optimization","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944633","doi":"https://doi.org/10.18653/v1/2025.findings-acl.1225"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.1225","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1225","pdf_url":"https://aclanthology.org/2025.findings-acl.1225.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.1225.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112503248","display_name":"Hieu Trung Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hieu Trung Nguyen","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103431981","display_name":"Bao D. Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bao Nguyen","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100625770","display_name":"Viet Anh Nguyen","orcid":"https://orcid.org/0000-0002-2515-9494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Viet Anh Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"23911","last_page":"23922"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.5843999981880188,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.5843999981880188,"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/T10703","display_name":"Business Process Modeling and Analysis","score":0.5370000004768372,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.5260000228881836,"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/computer-science","display_name":"Computer science","score":0.7195661067962646},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6649050116539001},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4711529016494751},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3466786742210388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7195661067962646},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6649050116539001},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4711529016494751},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3466786742210388},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.1225","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1225","pdf_url":"https://aclanthology.org/2025.findings-acl.1225.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.1225","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.1225","pdf_url":"https://aclanthology.org/2025.findings-acl.1225.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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944633.pdf","grobid_xml":"https://content.openalex.org/works/W4412944633.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Model":[0],"pruning":[1,30],"in":[2,38,81],"transformer-based":[3],"language":[4],"models,":[5],"traditionally":[6],"viewed":[7],"as":[8],"a":[9,25,51],"means":[10],"of":[11,31],"achieving":[12],"computational":[13],"savings,":[14],"can":[15],"enhance":[16],"the":[17,28,59,100],"model's":[18],"reasoning":[19,39],"capabilities.In":[20],"this":[21,46],"work,":[22],"we":[23,48],"uncover":[24],"surprising":[26],"phenomenon:":[27],"selective":[29],"certain":[32],"attention":[33],"heads":[34],"leads":[35],"to":[36,64],"improvements":[37],"performance,":[40],"particularly":[41],"on":[42,99],"challenging":[43],"tasks.Motivated":[44],"by":[45],"observation,":[47],"propose":[49],"SPRINT,":[50],"novel":[52],"contrastive":[53],"learning":[54],"framework":[55],"that":[56,79,87],"dynamically":[57],"selects":[58],"optimal":[60],"head":[61,72,96],"and":[62,94,102],"layer":[63],"prune":[65],"during":[66],"inference.By":[67],"aligning":[68],"question":[69],"embeddings":[70],"with":[71],"embeddings,":[73],"SPRINT":[74],"identifies":[75],"those":[76],"pruned-head":[77],"configurations":[78],"result":[80],"more":[82],"accurate":[83],"reasoning.Extensive":[84],"experiments":[85],"demonstrate":[86],"our":[88],"method":[89],"significantly":[90],"outperforms":[91],"traditional":[92],"best-of-N":[93],"random":[95],"selection":[97],"strategies":[98],"MATH500":[101],"GSM8K":[103],"datasets.":[104]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}