{"id":"https://openalex.org/W4402671396","doi":"https://doi.org/10.18653/v1/2024.acl-srw.28","title":"On Improving Repository-Level Code QA for Large Language Models","display_name":"On Improving Repository-Level Code QA for Large Language Models","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402671396","doi":"https://doi.org/10.18653/v1/2024.acl-srw.28"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.acl-srw.28","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.acl-srw.28","pdf_url":"https://aclanthology.org/2024.acl-srw.28.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.acl-srw.28.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107453192","display_name":"Jan Strich","orcid":null},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jan Strich","raw_affiliation_strings":["Language Technology Group Universitt Hamburg Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Universitt Hamburg Germany","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030537880","display_name":"Florian Schneider","orcid":"https://orcid.org/0000-0003-3036-6284"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Schneider","raw_affiliation_strings":["Language Technology Group Universitt Hamburg Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Universitt Hamburg Germany","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103279780","display_name":"Irina Nikishin\u0430","orcid":"https://orcid.org/0000-0002-0238-4760"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Irina Nikishina","raw_affiliation_strings":["Language Technology Group Universitt Hamburg Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Universitt Hamburg Germany","institution_ids":["https://openalex.org/I884043246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021287757","display_name":"Chris Biemann","orcid":"https://orcid.org/0000-0002-8449-9624"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chris Biemann","raw_affiliation_strings":["Language Technology Group Universitt Hamburg Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technology Group Universitt Hamburg Germany","institution_ids":["https://openalex.org/I884043246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12970936,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"303","last_page":"338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9929999709129333,"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":0.9929999709129333,"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/T10028","display_name":"Topic Modeling","score":0.9722999930381775,"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9200000166893005,"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/computer-science","display_name":"Computer science","score":0.7829440832138062},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5702998042106628},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5460793972015381},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.34886717796325684},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34619367122650146}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7829440832138062},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5702998042106628},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5460793972015381},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34886717796325684},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34619367122650146},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.acl-srw.28","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.acl-srw.28","pdf_url":"https://aclanthology.org/2024.acl-srw.28.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.acl-srw.28","is_oa":true,"landing_page_url":"http://dx.doi.org/10.18653/v1/2024.acl-srw.28","pdf_url":"https://aclanthology.org/2024.acl-srw.28.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 62nd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402671396.pdf","grobid_xml":"https://content.openalex.org/works/W4402671396.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"such":[4],"as":[5,14,45,47,67],"Chat-GPT,":[6],"GitHub":[7],"Copilot,":[8],"Llama,":[9],"or":[10],"Mistral":[11],"assist":[12],"programmers":[13],"copilots":[15],"and":[16,25,40,60,87,103,109],"knowledge":[17],"sources":[18],"to":[19,30,72,77],"make":[20],"the":[21,32,51,74,79,83,88,92,106],"coding":[22],"process":[23],"faster":[24],"more":[26],"efficient.This":[27],"paper":[28],"aims":[29],"improve":[31],"copilot":[33],"performance":[34],"by":[35],"implementing":[36],"different":[37],"self-alignment":[38],"processes":[39],"retrievalaugmented":[41],"generation":[42],"(RAG)":[43],"pipelines,":[44],"well":[46],"their":[48],"combination.To":[49],"test":[50],"effectiveness":[52],"of":[53],"all":[54],"approaches,":[55],"we":[56],"create":[57],"a":[58,62,68],"dataset":[59,110],"apply":[61],"model-based":[63],"evaluation,":[64],"using":[65],"LLM":[66],"judge.It":[69],"is":[70],"designed":[71],"check":[73],"model's":[75],"abilities":[76],"understand":[78],"source":[80],"code":[81],"semantics,":[82],"dependency":[84],"between":[85],"files,":[86],"overall":[89],"meta-information":[90],"about":[91],"repository.We":[93],"also":[94],"compare":[95],"our":[96],"approach":[97],"with":[98],"other":[99],"existing":[100,107],"solutions,":[101],"e.g.ChatGPT-3.5,":[102],"evaluate":[104],"on":[105],"benchmarks.Code":[108],"are":[111],"available":[112],"online":[113],"1":[114],".":[115]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
