{"id":"https://openalex.org/W4416692581","doi":"https://doi.org/10.1145/3808144","title":"SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation","display_name":"SWR-Bench: Assessing LLM Performance in Real-World Code Review Comment Generation","publication_year":2026,"publication_date":"2026-06-30","ids":{"openalex":"https://openalex.org/W4416692581","doi":"https://doi.org/10.1145/3808144"},"language":"en","primary_location":{"id":"doi:10.1145/3808144","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808144","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3808144","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010506833","display_name":"Zhengran Zeng","orcid":"https://orcid.org/0009-0009-8422-4522"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengran Zeng","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-8422-4522","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruikai Shi","orcid":"https://orcid.org/0009-0001-2028-670X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruikai Shi","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-2028-670X","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Keke Han","orcid":"https://orcid.org/0009-0003-1843-8545"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Keke Han","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-1843-8545","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459848","display_name":"Yixin Li","orcid":"https://orcid.org/0009-0000-9663-9324"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixin Li","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-0492-2234","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaicheng Sun","orcid":"https://orcid.org/0009-0007-0856-9049"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaicheng Sun","raw_affiliation_strings":["Northwestern Polytechnical University, Xian, China"],"raw_orcid":"https://orcid.org/0009-0007-0856-9049","affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University, Xian, China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685716","display_name":"Yidong Wang","orcid":"https://orcid.org/0009-0007-9969-8259"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yidong Wang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-9969-8259","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010912592","display_name":"Zhuohao Yu","orcid":"https://orcid.org/0009-0006-0037-0396"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuohao Yu","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-8256-8588","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078075179","display_name":"Rui Xie","orcid":"https://orcid.org/0000-0002-2857-7480"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xie","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1756-7746","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100448683","display_name":"Wei Ye","orcid":"https://orcid.org/0000-0001-8096-0922"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Ye","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9331-4716","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058096102","display_name":"Shikun Zhang","orcid":"https://orcid.org/0000-0002-6628-4881"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikun Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8576-2674","affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.00348451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"3","issue":"FSE","first_page":"3093","last_page":"3115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.652400016784668,"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":0.652400016784668,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.05040000006556511,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.041600000113248825,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8213000297546387},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6721000075340271},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5080000162124634},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.45649999380111694},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4187000095844269},{"id":"https://openalex.org/keywords/mainstream","display_name":"Mainstream","score":0.34940001368522644}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8213000297546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7322999835014343},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6721000075340271},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.527899980545044},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5080000162124634},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.45649999380111694},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4246000051498413},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4187000095844269},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C2777617010","wikidata":"https://www.wikidata.org/wiki/Q18957","display_name":"Mainstream","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.32519999146461487},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.29910001158714294},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.27149999141693115},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C10272871","wikidata":"https://www.wikidata.org/wiki/Q929972","display_name":"Software inspection","level":5,"score":0.2662000060081482},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2605000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2506999969482422}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3808144","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808144","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2509.01494","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2509.01494","pdf_url":"https://arxiv.org/pdf/2509.01494","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.01494","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.01494","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,"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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1145/3808144","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3808144","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"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 ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Automated":[0],"Code":[1],"Review":[2],"(ACR)":[3],"is":[4],"crucial":[5],"for":[6,172],"software":[7],"quality,":[8],"yet":[9],"existing":[10],"benchmarks":[11,28],"often":[12],"fail":[13],"to":[14,145],"reflect":[15],"real-world":[16],"complexities,":[17],"hindering":[18],"the":[19,150],"evaluation":[20,42,75,101,155],"of":[21,102,160],"modern":[22],"Large":[23],"Language":[24],"Models":[25],"(LLMs).":[26],"Current":[27],"frequently":[29],"focus":[30],"on":[31,108],"fine-grained":[32],"code":[33],"units,":[34],"lack":[35],"complete":[36],"project":[37,68],"context,":[38],"and":[39,106,115,128,164],"use":[40],"inadequate":[41],"metrics.":[43],"To":[44],"address":[45],"these":[46],"limitations,":[47],"we":[48,126],"introduce":[49],"SWR-Bench,":[50],"a":[51,90,130,157],"new":[52],"benchmark":[53],"comprising":[54],"1000":[55],"manually":[56],"verified":[57],"Pull":[58],"Requests":[59],"(PRs)":[60],"from":[61,89],"GitHub,":[62],"offering":[63,169],"PR-centric":[64],"review":[65],"with":[66,80],"full":[67],"context.":[69],"SWR-Bench":[70,109,151],"employs":[71],"an":[72,165],"objective":[73,154],"LLM-based":[74],"method":[76],"that":[77,111,135],"aligns":[78],"strongly":[79],"human":[81],"judgment":[82],"(\u223c90%":[83],"agreement)":[84],"by":[85,143],"verifying":[86],"if":[87],"issues":[88],"structured":[91],"ground":[92],"truth":[93],"are":[94,118],"covered":[95],"in":[96],"generated":[97],"reviews.":[98],"Our":[99,147],"systematic":[100],"mainstream":[103],"ACR":[104,116,138,162,174],"tools":[105,117],"LLMs":[107],"reveals":[110],"current":[112,161],"systems":[113],"underperform,":[114],"more":[119],"adept":[120],"at":[121],"detecting":[122],"functional":[123],"errors.":[124],"Subsequently,":[125],"propose":[127],"validate":[129],"simple":[131],"multi-review":[132],"aggregation":[133],"strategy":[134],"significantly":[136],"boosts":[137],"performance,":[139],"increasing":[140],"F1":[141],"scores":[142],"up":[144],"43.67%.":[146],"contributions":[148],"include":[149],"benchmark,":[152],"its":[153],"method,":[156],"comprehensive":[158],"study":[159],"capabilities,":[163],"effective":[166],"enhancement":[167],"approach,":[168],"valuable":[170],"insights":[171],"advancing":[173],"research.":[175]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
