{"id":"https://openalex.org/W4412886820","doi":"https://doi.org/10.18653/v1/2025.acl-long.78","title":"LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models","display_name":"LEANCODE: Understanding Models Better for Code Simplification of Pre-trained Large Language Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886820","doi":"https://doi.org/10.18653/v1/2025.acl-long.78"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.78","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.78","pdf_url":"https://aclanthology.org/2025.acl-long.78.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.78.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100322749","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0002-6408-7366"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101844480","display_name":"Ling Ding","orcid":"https://orcid.org/0000-0002-4871-2352"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tien N Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tien N Nguyen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070990953","display_name":"Shaohua Wang","orcid":"https://orcid.org/0000-0001-5777-7759"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaohua Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016643106","display_name":"Yanan Zheng","orcid":"https://orcid.org/0000-0002-9823-0191"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanan Zheng","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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1551","last_page":"1567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9965000152587891,"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/T13629","display_name":"Text Readability and Simplification","score":0.9965000152587891,"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":0.9745000004768372,"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":0.9624000191688538,"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":0.7750301361083984},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5817936658859253},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5505509376525879},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5285208225250244},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4747788608074188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43651485443115234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750301361083984},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5817936658859253},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5505509376525879},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5285208225250244},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4747788608074188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43651485443115234},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.78","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.78","pdf_url":"https://aclanthology.org/2025.acl-long.78.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.14759","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.14759","pdf_url":"https://arxiv.org/pdf/2505.14759","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2505.14759","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.78","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.78","pdf_url":"https://aclanthology.org/2025.acl-long.78.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G4604030585","display_name":null,"funder_award_id":"NCAE-C-002-2021","funder_id":"https://openalex.org/F4320311089","funder_display_name":"National Security Agency"},{"id":"https://openalex.org/G5204842600","display_name":null,"funder_award_id":"CNS-2120386","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G758310216","display_name":"Collaborative Research: CCRI: ENS: Boa 2.0: Enhancing Infrastructure for Studying Software and its Evolution at a Large Scale","funder_award_id":"2120386","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311089","display_name":"National Security Agency","ror":"https://ror.org/0047bvr32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886820.pdf","grobid_xml":"https://content.openalex.org/works/W4412886820.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W4231937131","https://openalex.org/W3188962172","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W2772917594","https://openalex.org/W1487966966","https://openalex.org/W4312825515","https://openalex.org/W1589342014","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"for":[3,23,45,75,92,114,121],"code":[4,19,24,33,80,96,115,122],"often":[5],"entail":[6],"significant":[7],"computational":[8],"complexity,":[9],"which":[10],"grows":[11],"significantly":[12],"with":[13,108],"the":[14,17,41,46,53,66,73,84,103],"length":[15],"of":[16,49,69,110],"input":[18],"sequence.We":[20],"propose":[21],"LEANCODE":[22],"simplification":[25],"to":[26,39,88],"reduce":[27],"training":[28],"and":[29,106,112,117,119],"prediction":[30],"time,":[31],"leveraging":[32],"contexts":[34],"in":[35],"utilizing":[36],"attention":[37,56,67,86],"scores":[38,57,61,68,87],"represent":[40],"tokens'":[42],"importance.We":[43],"advocate":[44],"selective":[47],"removal":[48],"tokens":[50,71],"based":[51],"on":[52],"average":[54,60],"context-aware":[55],"rather":[58],"than":[59],"across":[62],"all":[63],"inputs.LEANCODE":[64],"uses":[65],"'CLS'":[70],"within":[72],"encoder":[74],"classification":[76],"tasks,":[77],"such":[78],"as":[79],"search.It":[81],"also":[82],"employs":[83],"encoderdecoder":[85],"determine":[89],"token":[90],"significance":[91],"sequence-to-sequence":[93],"tasks":[94],"like":[95],"summarization.Our":[97],"evaluation":[98],"shows":[99],"LEANCODE's":[100],"superiority":[101],"over":[102],"SOTAs":[104],"DI-ETCODE":[105],"SLIMCODE,":[107],"improvements":[109],"60%":[111],"16%":[113],"search,":[116],"29%":[118],"27%":[120],"summarization,":[123],"respectively.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}