{"id":"https://openalex.org/W4412886913","doi":"https://doi.org/10.18653/v1/2025.acl-long.48","title":"Rethinking Repetition Problems of LLMs in Code Generation","display_name":"Rethinking Repetition Problems of LLMs in Code Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886913","doi":"https://doi.org/10.18653/v1/2025.acl-long.48"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.48","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.48","pdf_url":"https://aclanthology.org/2025.acl-long.48.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.48.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077542599","display_name":"Yihong Dong","orcid":"https://orcid.org/0000-0002-6048-2377"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yihong Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373068","display_name":"Yuchen Liu","orcid":"https://orcid.org/0009-0004-0955-5624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuchen Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082599057","display_name":"Xue Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101875578","display_name":"Bin Gu","orcid":"https://orcid.org/0000-0003-1621-7311"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049100391","display_name":"Zhi Jin","orcid":"https://orcid.org/0000-0003-1087-226X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447682","display_name":"Ge Li","orcid":"https://orcid.org/0000-0002-5828-0186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ge Li","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":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"965","last_page":"985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9643999934196472,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9643999934196472,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.9060999751091003,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/repetition","display_name":"Repetition (rhetorical device)","score":0.6571515798568726},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5482020974159241},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5020864009857178},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3298030495643616},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08917742967605591}],"concepts":[{"id":"https://openalex.org/C2776141515","wikidata":"https://www.wikidata.org/wiki/Q1274479","display_name":"Repetition (rhetorical device)","level":2,"score":0.6571515798568726},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5482020974159241},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5020864009857178},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3298030495643616},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08917742967605591},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.48","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.48","pdf_url":"https://aclanthology.org/2025.acl-long.48.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.48","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.48","pdf_url":"https://aclanthology.org/2025.acl-long.48.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":[],"awards":[{"id":"https://openalex.org/G3446613798","display_name":null,"funder_award_id":"62192730","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8449925957","display_name":null,"funder_award_id":"62192733","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886913.pdf","grobid_xml":"https://content.openalex.org/works/W4412886913.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/W2996195527","https://openalex.org/W2978375718","https://openalex.org/W2351132524","https://openalex.org/W2612358220","https://openalex.org/W2916738897","https://openalex.org/W2392934913","https://openalex.org/W2003474770"],"abstract_inverted_index":{"With":[0],"the":[1,7,16,21,40,57,101,125,155,168,186],"advent":[2],"of":[3,9,18,39,127,188],"neural":[4],"language":[5],"models,":[6],"performance":[8],"code":[10,45,59,105,119,138,159],"generation":[11,22,106],"has":[12,28],"been":[13],"significantly":[14],"boosted.However,":[15],"problem":[17,43,51],"repetitions":[19,183],"during":[20,118],"process":[23],"continues":[24],"to":[25,99,114,132,149],"linger.Previous":[26],"work":[27],"primarily":[29],"focused":[30],"on":[31,97,171],"content":[32],"repetition,":[33,56],"which":[34,69,91],"is":[35,52],"merely":[36],"a":[37,66,145],"fraction":[38],"broader":[41],"repetition":[42,82,102,116,156],"in":[44,61,74,104,137,158],"generation.A":[46],"more":[47],"prevalent":[48],"and":[49,83,121,178,184],"challenging":[50],"structural":[53,55,81],"repetition.In":[54],"repeated":[58],"appears":[60],"various":[62],"patterns":[63],"but":[64],"possesses":[65],"fixed":[67],"structure,":[68],"can":[70],"be":[71],"inherently":[72],"reflected":[73],"grammar.In":[75],"this":[76,141],"paper,":[77],"we":[78,143],"formally":[79],"define":[80],"propose":[84],"an":[85],"efficient":[86],"decoding":[87],"approach":[88],"called":[89],"RPG,":[90],"stands":[92],"for":[93,107,153],"Repetition":[94],"Penalization":[95],"based":[96],"Grammar,":[98],"alleviate":[100],"problems":[103,117,157],"LLMs.Specifically,":[108],"RPG":[109,165],"first":[110],"leverages":[111],"grammar":[112],"rules":[113],"identify":[115],"generation,":[120],"then":[122],"strategically":[123],"decays":[124],"likelihood":[126],"critical":[128],"tokens":[129],"that":[130,164],"contribute":[131],"repetitions,":[133],"thereby":[134],"mitigating":[135,154],"them":[136],"generation.To":[139],"facilitate":[140],"study,":[142],"construct":[144],"new":[146],"dataset":[147,173],"CodeRepetEval":[148,172],"comprehensively":[150],"evaluate":[151],"approaches":[152],"generation.Extensive":[160],"experimental":[161],"results":[162],"demonstrate":[163],"substantially":[166],"outperforms":[167],"best-performing":[169],"baselines":[170],"as":[174,176],"well":[175],"HumanEval":[177],"MBPP":[179],"benchmarks,":[180],"effectively":[181],"reducing":[182],"enhancing":[185],"quality":[187],"generated":[189],"code.":[190],"1":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}