{"id":"https://openalex.org/W7126193118","doi":"https://doi.org/10.1145/3793655.3793716","title":"Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering","display_name":"Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7126193118","doi":"https://doi.org/10.1145/3793655.3793716"},"language":null,"primary_location":{"id":"doi:10.1145/3793655.3793716","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793716","pdf_url":null,"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 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3793655.3793716","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124405216","display_name":"Daniel Rodriguez-Cardenas","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Rodriguez-Cardenas","raw_affiliation_strings":["William & Mary, Williamsburg, USA"],"raw_orcid":"https://orcid.org/0000-0002-3238-1229","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124361159","display_name":"Xiaochang Li","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaochang Li","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0009-0009-8073-8817","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103255623","display_name":"Marcos Macedo","orcid":"https://orcid.org/0009-0001-1008-1073"},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Marcos Macedo","raw_affiliation_strings":["Queen's University, Kingston, Ontario, Canada"],"raw_orcid":"https://orcid.org/0009-0001-1008-1073","affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, Ontario, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069505458","display_name":"Antonio Mastropaolo","orcid":"https://orcid.org/0000-0002-7965-7712"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio Mastropaolo","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-7965-7712","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124094640","display_name":"Dipin Khati","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dipin Khati","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0009-0008-4489-7733","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124355362","display_name":"Yuan Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I204722609","display_name":"Queen's University","ror":"https://ror.org/02y72wh86","country_code":"CA","type":"education","lineage":["https://openalex.org/I204722609"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Yuan Tian","raw_affiliation_strings":["Queen's University, Kingston, Ontario, Canada"],"raw_orcid":"https://orcid.org/0000-0002-2208-3893","affiliations":[{"raw_affiliation_string":"Queen's University, Kingston, Ontario, Canada","institution_ids":["https://openalex.org/I204722609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124395387","display_name":"Huajie Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huajie Shao","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0001-7627-5615","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124384889","display_name":"Denys Poshyvanyk","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]},{"id":"https://openalex.org/I267592682","display_name":"Williams (United States)","ror":"https://ror.org/007zhvp17","country_code":"US","type":"company","lineage":["https://openalex.org/I267592682"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Denys Poshyvanyk","raw_affiliation_strings":["William & Mary, Williamsburg, Virginia, USA"],"raw_orcid":"https://orcid.org/0000-0002-5626-7586","affiliations":[{"raw_affiliation_string":"William & Mary, Williamsburg, Virginia, USA","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":"243","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.5418000221252441,"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":0.5418000221252441,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.1981000006198883,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.026599999517202377,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8027999997138977},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6256999969482422},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5218999981880188},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.45159998536109924},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.44920000433921814},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4198000133037567},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3422999978065491},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.34049999713897705}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8027999997138977},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6256999969482422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5784000158309937},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5218999981880188},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.45159998536109924},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.44920000433921814},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4361000061035156},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4138000011444092},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3456999957561493},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3422999978065491},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.34049999713897705},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.33799999952316284},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.32850000262260437},{"id":"https://openalex.org/C110354214","wikidata":"https://www.wikidata.org/wiki/Q6314146","display_name":"Engineering management","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3192000091075897},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2750000059604645},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2581000030040741}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3793655.3793716","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793716","pdf_url":null,"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 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2601.21070","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.21070","pdf_url":"https://arxiv.org/pdf/2601.21070","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"doi:10.1145/3793655.3793716","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3793655.3793716","pdf_url":null,"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 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.6476627588272095,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,128],"for":[3],"code":[4],"are":[5],"advancing":[6],"fast,":[7],"yet":[8],"our":[9],"ability":[10],"to":[11,83,126,143,149],"evaluate":[12],"them":[13],"lags":[14],"behind.":[15],"Current":[16],"benchmarks":[17,69,151],"focus":[18],"on":[19,92,104],"narrow":[20],"tasks":[21],"and":[22,34,49,57,95,133,136,157],"single":[23],"metrics,":[24,94],"which":[25],"hide":[26],"critical":[27],"gaps":[28],"in":[29,162],"robustness,":[30],"interpretability,":[31],"fairness,":[32],"efficiency,":[33],"real-world":[35],"usability.":[36],"They":[37],"also":[38],"suffer":[39],"from":[40,73],"inconsistent":[41],"data":[42,101],"engineering":[43,47],"practices,":[44],"limited":[45],"software":[46,163],"context,":[48],"widespread":[50],"contamination":[51],"issues.":[52],"To":[53],"understand":[54],"these":[55,105],"problems":[56],"chart":[58],"a":[59,74,110,123,154],"path":[60],"forward,":[61],"we":[62,107],"combined":[63],"an":[64],"in-depth":[65],"survey":[66],"of":[67,88,98,160],"existing":[68],"with":[70,118],"insights":[71],"gathered":[72],"dedicated":[75],"community":[76],"workshop.":[77],"We":[78],"identified":[79],"three":[80],"core":[81],"barriers":[82],"reliable":[84],"evaluation:":[85],"the":[86,96,145],"absence":[87],"software-engineering-rich":[89],"datasets,":[90],"overreliance":[91],"ML-centric":[93],"lack":[97],"standardized,":[99],"reproducible":[100],"pipelines.":[102],"Building":[103],"findings,":[106],"introduce":[108],"BEHELM,":[109],"holistic":[111],"benchmarking":[112],"infrastructure":[113],"that":[114],"unifies":[115],"software-scenario":[116],"specification":[117],"multi-metric":[119],"evaluation.":[120],"BEHELM":[121],"provides":[122],"structured":[124],"way":[125],"assess":[127],"across":[129],"tasks,":[130],"languages,":[131],"input":[132],"output":[134],"granularities,":[135],"key":[137],"quality":[138],"dimensions.":[139],"Our":[140],"goal":[141],"is":[142],"reduce":[144],"overhead":[146],"currently":[147],"required":[148],"construct":[150],"while":[152],"enabling":[153],"fair,":[155],"realistic,":[156],"future-proof":[158],"assessment":[159],"LLMs":[161],"engineering.":[164]},"counts_by_year":[],"updated_date":"2026-07-22T06:00:27.337203","created_date":"2026-02-01T00:00:00"}