{"id":"https://openalex.org/W4416034875","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.430","title":"cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree","display_name":"cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034875","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.430"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.430","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.430","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.430","pdf_url":"https://aclanthology.org/2025.findings-emnlp.430.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2025.findings-emnlp.430.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100758237","display_name":"Yilin Zhang","orcid":"https://orcid.org/0000-0002-8238-2326","observed_orcids":["https://orcid.org/0000-0002-8238-2326","https://orcid.org/0009-0004-3020-4917"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yilin Zhang","raw_affiliation_strings":["Carnegie Mellon University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University ,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102892146","display_name":"Xinran Zhao","orcid":"https://orcid.org/0009-0006-0938-7602","observed_orcids":["https://orcid.org/0009-0006-0938-7602"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinran Zhao","raw_affiliation_strings":["Carnegie Mellon University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University ,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042968859","display_name":"Zora Zhiruo Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zora Zhiruo Wang","raw_affiliation_strings":["Carnegie Mellon University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University ,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082950698","display_name":"Chenyang Yang","orcid":"https://orcid.org/0000-0003-0058-0765","observed_orcids":["https://orcid.org/0000-0003-0058-0765"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chenyang Yang","raw_affiliation_strings":["Carnegie Mellon University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University ,","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091838811","display_name":"Jiayi Wei","orcid":"https://orcid.org/0000-0001-5295-4891","observed_orcids":["https://orcid.org/0000-0001-5295-4891"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayi Wei","raw_affiliation_strings":["Augment Code"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Augment Code","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004225142","display_name":"Tongshuang Wu","orcid":"https://orcid.org/0000-0003-1630-0588","observed_orcids":["https://orcid.org/0000-0003-1630-0588"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tongshuang Wu","raw_affiliation_strings":["Carnegie Mellon University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University ,","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":17.545,"has_fulltext":true,"cited_by_count":32,"citation_normalized_percentile":{"value":0.99338265,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"8106","last_page":"8116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.00019999999494757503,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/retrieval-augmented-generation","display_name":"retrieval-augmented generation","score":0.953000009059906},{"id":"https://openalex.org/keywords/abstract-syntax-tree","display_name":"abstract syntax tree","score":0.8619999885559082},{"id":"https://openalex.org/keywords/code-generation","display_name":"code generation","score":0.7009999752044678},{"id":"https://openalex.org/keywords/code-search","display_name":"code search","score":0.5450000166893005},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.5759999752044678},{"id":"https://openalex.org/keywords/semantic-chunking","display_name":"semantic chunking","score":0.42100000381469727},{"id":"https://openalex.org/keywords/swe-bench","display_name":"SWE-bench","score":0.996999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7257000207901001},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5245000123977661},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44609999656677246},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C58646249","wikidata":"https://www.wikidata.org/wiki/Q127380","display_name":"Abstract syntax tree","level":3,"score":0.38749998807907104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3869999945163727},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3061999976634979},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3028999865055084},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C114408938","wikidata":"https://www.wikidata.org/wiki/Q333373","display_name":"Abstract syntax","level":3,"score":0.287200003862381},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.28619998693466187},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26269999146461487}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.430","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.430","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.430","pdf_url":"https://aclanthology.org/2025.findings-emnlp.430.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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"},{"id":"pmh:oai:arXiv.org:2506.15655","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.15655","pdf_url":"https://arxiv.org/pdf/2506.15655","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.15655","doi":"https://doi.org/10.48550/arxiv.2506.15655","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.15655","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.430","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.430","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.430","pdf_url":"https://aclanthology.org/2025.findings-emnlp.430.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034875.pdf","grobid_xml":"https://content.openalex.org/works/W4416034875.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W3177813494","https://openalex.org/W4311731003","https://openalex.org/W4376167329","https://openalex.org/W4386185625","https://openalex.org/W4388183278","https://openalex.org/W4390723549","https://openalex.org/W4391591817","https://openalex.org/W4395443287","https://openalex.org/W4396717806","https://openalex.org/W4396786113","https://openalex.org/W4400526126","https://openalex.org/W4401042773","https://openalex.org/W4402671700","https://openalex.org/W4404782650","https://openalex.org/W4404783040","https://openalex.org/W4404783077","https://openalex.org/W4407942537","https://openalex.org/W4411113095","https://openalex.org/W4411449940","https://openalex.org/W6967084484","https://openalex.org/W7131877086","https://openalex.org/W7212295216"],"related_works":["https://openalex.org/W7160536460","https://openalex.org/W7155060382","https://openalex.org/W7214530910","https://openalex.org/W4416621686","https://openalex.org/W7130529660","https://openalex.org/W4411113095","https://openalex.org/W7212322835","https://openalex.org/W4416374286","https://openalex.org/W7125362215","https://openalex.org/W4409047580"],"abstract_inverted_index":{"Retrieval-Augmented":[0],"Generation":[1],"(RAG)":[2],"has":[3],"become":[4],"essential":[5],"for":[6,123],"large-scale":[7],"code":[8,14,96,126],"generation,":[9],"grounding":[10],"predictions":[11],"in":[12],"external":[13],"corpora":[15],"to":[16],"improve":[17],"factuality.However,":[18],"a":[19,61],"critical":[20],"yet":[21],"underexplored":[22],"aspect":[23],"of":[24,30,120],"RAG":[25],"pipelines":[26],"is":[27],"chunking-the":[28],"process":[29],"dividing":[31],"documents":[32],"into":[33,70],"retrievable":[34],"units.Existing":[35],"linebased":[36],"chunking":[37,55,122],"heuristics":[38],"often":[39],"break":[40],"semantic":[41],"structures,":[42],"splitting":[43],"functions":[44],"or":[45],"merging":[46],"unrelated":[47],"code,":[48],"which":[49],"can":[50],"degrade":[51],"generation":[52,97],"quality.We":[53],"propose":[54],"via":[56],"Abstract":[57],"Syntax":[58],"Trees":[59],"(CAST),":[60],"structure-aware":[62,121],"method":[63],"that":[64],"recursively":[65],"breaks":[66],"large":[67],"AST":[68],"nodes":[69,76],"smaller":[71],"chunks":[72],"and":[73,90,108],"merges":[74],"sibling":[75],"while":[77],"respecting":[78],"size":[79],"limits.This":[80],"approach":[81],"generates":[82],"selfcontained,":[83],"semantically":[84],"coherent":[85],"units":[86],"across":[87],"programming":[88],"languages":[89],"tasks,":[91,98],"improving":[92],"performance":[93],"on":[94,105,113],"diverse":[95],"e.g.,":[99],"boosting":[100],"Recall@5":[101],"by":[102,110],"4.3":[103],"points":[104,112],"Re-poEval":[106],"retrieval":[107],"Pass@1":[109],"2.67":[111],"SWE-bench":[114],"generation.Our":[115],"work":[116],"highlights":[117],"the":[118],"importance":[119],"scaling":[124],"retrieval-enhanced":[125],"intelligence.":[127]},"counts_by_year":[{"year":2026,"cited_by_count":29},{"year":2025,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-11-08T00:00:00"}