{"id":"https://openalex.org/W4416034234","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1147","title":"Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification","display_name":"Beyond Function-Level Search: Repository-Aware Dual-Encoder Code Retrieval with Adversarial Verification","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034234","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1147"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1147","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1147","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1147.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1147.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010675602","display_name":"A. Q. Liu","orcid":"https://orcid.org/0000-0002-0126-5778"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aofan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038625768","display_name":"Shiyuan Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song Shiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034150163","display_name":"Haoxuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoxuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113257046","display_name":"Cehao Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cehao Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056609151","display_name":"Yiyan Qi","orcid":"https://orcid.org/0000-0002-8078-5834"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiyan Qi","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":"21034","last_page":"21049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.2565000057220459,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.2565000057220459,"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/T10260","display_name":"Software Engineering Research","score":0.23319999873638153,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.060600001364946365,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/adversarial-system","display_name":"Adversarial system","score":0.4925999939441681},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4643999934196472},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3192000091075897},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.28850001096725464},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2806999981403351},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.27970001101493835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.669700026512146},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4643999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36390000581741333},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2806999981403351},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26179999113082886},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1147","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1147","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1147.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.1147","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1147","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1147.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":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034234.pdf","grobid_xml":"https://content.openalex.org/works/W4416034234.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"escalating":[1],"complexity":[2],"of":[3,15],"modern":[4],"codebases":[5],"has":[6,30],"intensified":[7],"the":[8,55,73],"need":[9],"for":[10,42,64],"code":[11,36,41,62],"retrieval":[12,63,77],"systems":[13],"capable":[14],"interpreting":[16],"crosscomponent":[17],"change":[18,44,65],"intents-a":[19],"capability":[20],"fundamentally":[21],"absent":[22],"in":[23],"conventional":[24],"functionlevel":[25],"search":[26],"paradigms.While":[27],"recent":[28],"research":[29],"improved":[31],"alignment":[32],"between":[33],"queries":[34],"and":[35,95,105,121],"snippets,":[37],"retrieving":[38],"contextually":[39],"relevant":[40],"certain":[43],"request":[45],"remains":[46],"underexplored.":[47],"To":[48],"bridge":[49],"this":[50],"gap,":[51],"we":[52,84],"present":[53],"RepoAlign-Bench,":[54],"first":[56],"benchmark":[57,71],"designed":[58],"to":[59,78],"evaluate":[60],"repository-level":[61],"request-driven":[66],"scenarios,":[67],"encompassing":[68],"52k":[69],"columns.The":[70],"shifts":[72],"paradigm":[74],"from":[75],"function-centric":[76],"holistic":[79],"repository":[80],"analysis.":[81],"In":[82],"addition,":[83],"propose":[85],"ReflectCode,":[86],"an":[87],"adversarial":[88],"reflection-augmented":[89],"dual-tower":[90],"architecture":[91],"featuring":[92],"disentangled":[93],"code_encoder":[94],"doc_encoder":[96],"towers.Our":[97],"framework":[98],"dynamically":[99],"integrates":[100],"syntactic":[101],"patterns,":[102],"function":[103],"dependency,":[104],"semantic":[106],"expansion":[107],"intent":[108],"through":[109],"LLM.":[110],"Comprehensive":[111],"evalu-":[112],"ations":[113],"demonstrate":[114],"that":[115],"ReflectCode":[116],"achieves":[117],"12.2%":[118],"Top-5":[119],"Accuracy":[120],"7.1%":[122],"Recall":[123],"improvements":[124],"over":[125],"state-of-the-art":[126],"baselines.Our":[127],"dataset":[128],"is":[129],"available":[130],"at:":[131],"RepoAlignBench-Full":[132]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}