{"id":"https://openalex.org/W4412376916","doi":"https://doi.org/10.1145/3726302.3730262","title":"Understanding Large Language Model Performance in Software Engineering: A Large-scale Question Answering Benchmark","display_name":"Understanding Large Language Model Performance in Software Engineering: A Large-scale Question Answering Benchmark","publication_year":2025,"publication_date":"2025-07-13","ids":{"openalex":"https://openalex.org/W4412376916","doi":"https://doi.org/10.1145/3726302.3730262"},"language":"en","primary_location":{"id":"doi:10.1145/3726302.3730262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730262","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730262","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730262","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078481838","display_name":"Ruida Hu","orcid":"https://orcid.org/0009-0000-9221-2788"},"institutions":[{"id":"https://openalex.org/I158809036","display_name":"Shenzhen Institute of Information Technology","ror":"https://ror.org/03wrf9427","country_code":"CN","type":"education","lineage":["https://openalex.org/I158809036"]},{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Ruida Hu","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China"],"raw_orcid":"https://orcid.org/0009-0000-9221-2788","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, Guangdong, China","institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103231827","display_name":"Chao Peng","orcid":"https://orcid.org/0000-0003-2843-0689"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Peng","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2843-0689","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingyi Ren","orcid":"https://orcid.org/0009-0006-5687-1026"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingyi Ren","raw_affiliation_strings":["ByteDance, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-5687-1026","affiliations":[{"raw_affiliation_string":"ByteDance, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101284039","display_name":"Bo Jiang","orcid":"https://orcid.org/0009-0000-1080-3278"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Jiang","raw_affiliation_strings":["ByteDance, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-1080-3278","affiliations":[{"raw_affiliation_string":"ByteDance, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009594735","display_name":"Xiangxin Meng","orcid":"https://orcid.org/0000-0001-5630-4810"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangxin Meng","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5630-4810","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100494936","display_name":"Qinyun Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinyun Wu","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7371-1036","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101924725","display_name":"Pengfei Gao","orcid":"https://orcid.org/0000-0003-3800-2565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengfei Gao","raw_affiliation_strings":["ByteDance, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3800-2565","affiliations":[{"raw_affiliation_string":"ByteDance, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695389","display_name":"Xinchen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinchen Wang","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-8915-6392","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061699251","display_name":"Cuiyun Gao","orcid":"https://orcid.org/0000-0003-4774-2434"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cuiyun Gao","raw_affiliation_strings":["Harbin Institute of Technology, Shenzhen, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4774-2434","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Shenzhen, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5078481838"],"corresponding_institution_ids":["https://openalex.org/I158809036","https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24317479,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3025","last_page":"3029"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9980000257492065,"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":0.9980000257492065,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9966999888420105,"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/T10028","display_name":"Topic Modeling","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.7650855183601379},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7389999628067017},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.7280535697937012},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4600211977958679},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4469781517982483},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41055041551589966},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.39599722623825073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39466679096221924},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3873730003833771}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7650855183601379},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7389999628067017},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.7280535697937012},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4600211977958679},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4469781517982483},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41055041551589966},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.39599722623825073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39466679096221924},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3873730003833771},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3726302.3730262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730262","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730262","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3726302.3730262","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3726302.3730262","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3726302.3730262","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3616843134","display_name":null,"funder_award_id":"2023A1515011959","funder_id":"https://openalex.org/F4320321921","funder_display_name":"Natural Science Foundation of Guangdong Province"},{"id":"https://openalex.org/G617086500","display_name":null,"funder_award_id":"62472126","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7148152373","display_name":null,"funder_award_id":"2023A1515011959","funder_id":"https://openalex.org/F4320323817","funder_display_name":"Universitas Brawijaya"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null},{"id":"https://openalex.org/F4320323817","display_name":"Universitas Brawijaya","ror":"https://ror.org/01wk3d929"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412376916.pdf","grobid_xml":"https://content.openalex.org/works/W4412376916.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2606092111","https://openalex.org/W2750779823","https://openalex.org/W4287887307","https://openalex.org/W4321013654","https://openalex.org/W4323033814","https://openalex.org/W4384345745","https://openalex.org/W6600424091"],"related_works":["https://openalex.org/W2384605597","https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2387743295","https://openalex.org/W2130974462","https://openalex.org/W4288267738","https://openalex.org/W2964413124","https://openalex.org/W4388937922","https://openalex.org/W3113264705"],"abstract_inverted_index":{"In":[0],"this":[1,41],"work,":[2],"we":[3,43],"introduce":[4],"CodeRepoQA,":[5],"a":[6,29,70,79],"large-scale":[7],"benchmark":[8,73],"specifically":[9],"designed":[10],"for":[11,55],"evaluating":[12],"repository-level":[13],"question-answering":[14,72],"capabilities":[15],"in":[16,50],"the":[17,52,64],"field":[18],"of":[19,32,37,82,89],"software":[20,83],"engineering.":[21],"CodeRepoQA":[22,68],"encompasses":[23],"five":[24],"programming":[25],"languages":[26],"and":[27,57,61],"covers":[28,78],"wide":[30],"range":[31],"scenarios,":[33,85],"enabling":[34],"comprehensive":[35],"evaluation":[36],"language":[38],"models.To":[39],"construct":[40],"dataset,":[42],"crawl":[44],"data":[45],"from":[46],"30":[47],"well-known":[48],"repositories":[49],"GitHub,":[51],"largest":[53],"platform":[54],"hosting":[56],"collaborating":[58],"on":[59],"code,":[60],"carefully":[62],"filter":[63],"raw":[65],"data.In":[66],"total,":[67],"is":[69],"multi-turn":[71],"with":[74,86],"585,687":[75],"entries.":[76],"It":[77],"diverse":[80],"array":[81],"engineering":[84],"an":[87],"average":[88],"6.62":[90],"dialogue":[91],"turns":[92],"per":[93],"entry.":[94]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
