{"id":"https://openalex.org/W4416034802","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.281","title":"Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation","display_name":"Beyond the Surface: A Solution-Aware Retrieval Model for Competition-level Code Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034802","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.281"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.281","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.281","pdf_url":"https://aclanthology.org/2025.findings-emnlp.281.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.281.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100689852","display_name":"Shiwen Zhang","orcid":"https://orcid.org/0000-0001-6892-2333"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiwen Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100306089","display_name":"Lingxiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingxiang Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101856227","display_name":"Hainan Zhang","orcid":"https://orcid.org/0000-0001-9659-4840"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hainan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044550346","display_name":"Ziwei Wang","orcid":"https://orcid.org/0000-0001-6005-0286"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziwei Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050941958","display_name":"Sijia Wen","orcid":"https://orcid.org/0000-0001-7032-5474"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sijia Wen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5086610984","display_name":"Zhi\u2010Ming Zheng","orcid":"https://orcid.org/0000-0001-5547-7912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiming Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.30213105,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5237","last_page":"5246"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.3041999936103821,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.3041999936103821,"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":0.2506999969482422,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.11829999834299088,"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/code","display_name":"Code (set theory)","score":0.4616999924182892},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.3122999966144562},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.29739999771118164},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24420000612735748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6600000262260437},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4616999924182892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34549999237060547},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3264000117778778},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3122999966144562},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.29739999771118164},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24420000612735748},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2425999939441681}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.281","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.281","pdf_url":"https://aclanthology.org/2025.findings-emnlp.281.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.281","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.281","pdf_url":"https://aclanthology.org/2025.findings-emnlp.281.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034802.pdf","grobid_xml":"https://content.openalex.org/works/W4416034802.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"competitive":[1,76,97,114],"programming":[2,115],"task,":[3],"problem":[4,95],"statements":[5],"are":[6,73],"often":[7],"embedded":[8],"within":[9],"elaborate":[10],"narrative":[11,40],"backgrounds,":[12],"requiring":[13],"deep":[14],"understanding":[15],"of":[16,82],"the":[17,23,67,119,159,168],"underlying":[18],"solutions":[19,49],"to":[20,36,122,161],"successfully":[21],"complete":[22],"tasks.Current":[24],"code":[25,46,98,157,165,185],"generation":[26,186],"models":[27,60,80],"primarily":[28],"focus":[29],"on":[30,55,167],"tokenlevel":[31],"semantic":[32,64],"modeling,":[33],"highly":[34],"susceptible":[35],"distractions":[37],"from":[38,158],"irrelevant":[39],"statements.Inspired":[41],"by":[42,110,132],"RAG,":[43],"retrieving":[44,86],"reference":[45],"with":[47,140],"similar":[48],"may":[50],"help":[51],"enhance":[52],"model":[53,108,121],"performance":[54,187],"difficult":[56,189],"problems.However,":[57],"existing":[58],"retrieval":[59],"also":[61],"emphasize":[62],"surface-level":[63],"similarity,":[65],"neglecting":[66],"deeper":[68],"solution-level":[69],"logical":[70],"similarities":[71],"that":[72,172],"critical":[74],"in":[75,96,178],"programming.Therefore,":[77],"designing":[78],"ranking":[79,107,176],"capable":[81],"accurately":[83],"identifying":[84],"and":[85,88,145,155,180,183],"problems":[87,147,154],"corresponding":[89,156],"codes":[90],"remains":[91],"an":[92],"urgent":[93],"research":[94],"generation.In":[99],"this":[100],"paper,":[101],"we":[102,117,137],"propose":[103],"SolveRank,":[104],"a":[105,163],"solution-aware":[106],"empowered":[109],"synthetic":[111],"data":[112],"for":[113,134,188],"tasks.Specifically,":[116],"leverage":[118],"DeepSeek-R1":[120],"generate":[123],"logically":[124],"equivalent":[125],"but":[126],"differently":[127],"phrased":[128],"new":[129],"problems,":[130],"verified":[131],"GPT-4o":[133],"solution":[135],"consistency.Then,":[136],"train":[138],"SolveRank":[139,151,173],"these":[141],"as":[142,148],"positive":[143],"samples":[144],"BM25/random-retrieved":[146],"negatives.During":[149],"inference,":[150],"retrieves":[152],"relevant":[153],"corpus":[160],"assist":[162],"downstream":[164],"generator.Experiments":[166],"xCodeEval":[169],"dataset":[170],"demonstrate":[171],"outperforms":[174],"SOTA":[175],"methods":[177],"precision":[179],"recall":[181],"metrics,":[182],"boosts":[184],"problems.":[190]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}