{"id":"https://openalex.org/W4412945609","doi":"https://doi.org/10.18653/v1/2025.acl-long.343","title":"Dynamic Scaling of Unit Tests for Code Reward Modeling","display_name":"Dynamic Scaling of Unit Tests for Code Reward Modeling","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412945609","doi":"https://doi.org/10.18653/v1/2025.acl-long.343"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.343","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.343","pdf_url":"https://aclanthology.org/2025.acl-long.343.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.343.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022455313","display_name":"Zeyao Ma","orcid":"https://orcid.org/0009-0006-9386-9136"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyao Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100412329","display_name":"Xiaokang Zhang","orcid":"https://orcid.org/0009-0009-3855-3093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaokang Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101985792","display_name":"Jing Zhang","orcid":"https://orcid.org/0009-0002-7087-2528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038246814","display_name":"Jifan Yu","orcid":"https://orcid.org/0000-0003-3430-4048"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jifan Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079294020","display_name":"Sijia Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sijia Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044791875","display_name":"Jie Tang","orcid":"https://orcid.org/0000-0003-3487-4593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Tang","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":"6917","last_page":"6935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10260","display_name":"Software Engineering Research","score":0.9807999730110168,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9775000214576721,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.6668176651000977},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5446006059646606},{"id":"https://openalex.org/keywords/unit-testing","display_name":"Unit testing","score":0.5361319184303284},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5243585109710693},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.4305571913719177},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39858362078666687},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2581111788749695},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.12180250883102417},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08410942554473877}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6668176651000977},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5446006059646606},{"id":"https://openalex.org/C148027188","wikidata":"https://www.wikidata.org/wiki/Q907375","display_name":"Unit testing","level":3,"score":0.5361319184303284},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5243585109710693},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.4305571913719177},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39858362078666687},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2581111788749695},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.12180250883102417},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08410942554473877},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"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/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.343","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.343","pdf_url":"https://aclanthology.org/2025.acl-long.343.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.343","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.343","pdf_url":"https://aclanthology.org/2025.acl-long.343.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/G1910011397","display_name":null,"funder_award_id":"U23A20299","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3763756418","display_name":null,"funder_award_id":"62276270","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8385808830","display_name":null,"funder_award_id":"62172424","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412945609.pdf","grobid_xml":"https://content.openalex.org/works/W4412945609.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2615173508","https://openalex.org/W141820298","https://openalex.org/W2049584446","https://openalex.org/W611386996","https://openalex.org/W2079781215","https://openalex.org/W4378770497","https://openalex.org/W2593332592","https://openalex.org/W4308245303","https://openalex.org/W2014033564","https://openalex.org/W2056396287"],"abstract_inverted_index":{"Current":[0],"large":[1],"language":[2],"models":[3,165],"(LLMs)":[4],"often":[5],"struggle":[6],"to":[7,43,85],"produce":[8],"accurate":[9],"solutions":[10,26,73],"on":[11,114,149,166,180],"the":[12,60,66,70,79,97,143],"first":[13],"attempt":[14],"for":[15,174,178],"code":[16],"generation.Prior":[17],"research":[18],"tackles":[19],"this":[20],"challenge":[21],"by":[22,65],"generating":[23],"multiple":[24],"candidate":[25],"and":[27,102,130,176],"validating":[28],"them":[29],"with":[30,106,170],"LLM-generated":[31],"unit":[32,37,53,83,100,124,132,146],"tests.The":[33],"execution":[34],"results":[35,155],"of":[36,62,72,81,99,145,172],"tests":[38,54,84,101,147],"serve":[39],"as":[40],"reward":[41,63,87,103],"signals":[42],"identify":[44],"correct":[45],"solutions.As":[46],"LLMs":[47],"always":[48],"confidently":[49],"make":[50],"mistakes,":[51],"these":[52,115],"are":[55],"not":[56],"reliable,":[57],"thereby":[58],"diminishing":[59],"quality":[61],"signals.Motivated":[64],"observation":[67],"that":[68,127,141,157],"scaling":[69,82,139],"number":[71,98,144],"improves":[74,161],"LLM":[75],"performance,":[76],"we":[77,117,135],"explore":[78],"impact":[80],"enhance":[86],"signal":[88,104],"quality.Our":[89],"pioneer":[90],"experiment":[91],"reveals":[92],"a":[93,120,137],"positive":[94],"correlation":[95],"between":[96],"quality,":[105],"greater":[107],"benefits":[108],"observed":[109],"in":[110],"more":[111],"challenging":[112],"problems.Based":[113],"insights,":[116],"propose":[118],"CodeRM-8B,":[119],"lightweight":[121],"yet":[122],"effective":[123],"test":[125,133],"generator":[126],"enables":[128],"efficient":[129],"high-quality":[131],"scaling.Additionally,":[134],"implement":[136],"dynamic":[138],"mechanism":[140],"adapts":[142],"based":[148],"problem":[150],"difficulty,":[151],"further":[152],"improving":[153],"efficiency.Experimental":[154],"show":[156],"our":[158],"approach":[159],"significantly":[160],"performance":[162],"across":[163],"various":[164],"three":[167],"benchmarks":[168],"(e.g.,":[169],"gains":[171],"18.43%":[173],"Llama3-8B":[175],"3.42%":[177],"GPT-4o-mini":[179],"HumanEval":[181],"Plus).":[182]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}