{"id":"https://openalex.org/W4398239135","doi":"https://doi.org/10.1145/3639478.3639792","title":"Beyond Accuracy and Robustness Metrics for Large Language Models for Code","display_name":"Beyond Accuracy and Robustness Metrics for Large Language Models for Code","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4398239135","doi":"https://doi.org/10.1145/3639478.3639792"},"language":"en","primary_location":{"id":"doi:10.1145/3639478.3639792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639478.3639792","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639478.3639792","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 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings","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/10.1145/3639478.3639792","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029623697","display_name":"Daniel Rodr\u00edguez-C\u00e1rdenas","orcid":"https://orcid.org/0000-0002-3238-1229"},"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":true,"raw_author_name":"Daniel Rodriguez-Cardenas","raw_affiliation_strings":["Semeru Lab, William & Mary, Williamsburg, VA, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-3238-1229","affiliations":[{"raw_affiliation_string":"Semeru Lab, William & Mary, Williamsburg, VA, United States of America","institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5029623697"],"corresponding_institution_ids":["https://openalex.org/I16285277","https://openalex.org/I267592682"],"apc_list":null,"apc_paid":null,"fwci":1.492,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.85281788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"159","last_page":"161"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9970999956130981,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9926000237464905,"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":0.784676194190979},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.774776816368103},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7681293487548828},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.6819508075714111},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.5412907004356384},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5105336904525757},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.47032392024993896},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4638410210609436},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4554223418235779},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.45148521661758423},{"id":"https://openalex.org/keywords/tracing","display_name":"Tracing","score":0.4196212589740753},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4067257344722748},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3453003764152527},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.34280073642730713},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.34204551577568054},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.25058436393737793},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19450750946998596},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.16353216767311096}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.784676194190979},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.774776816368103},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7681293487548828},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.6819508075714111},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.5412907004356384},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5105336904525757},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.47032392024993896},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4638410210609436},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4554223418235779},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.45148521661758423},{"id":"https://openalex.org/C138673069","wikidata":"https://www.wikidata.org/wiki/Q322229","display_name":"Tracing","level":2,"score":0.4196212589740753},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4067257344722748},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3453003764152527},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.34280073642730713},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.34204551577568054},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25058436393737793},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19450750946998596},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16353216767311096},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639478.3639792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639478.3639792","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639478.3639792","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 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3639478.3639792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3639478.3639792","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3639478.3639792","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 2024 IEEE/ACM 46th International Conference on Software Engineering: Companion Proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4398239135.pdf"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2511803001","https://openalex.org/W2736762043","https://openalex.org/W2888328667","https://openalex.org/W2907705732","https://openalex.org/W2954823997","https://openalex.org/W2972082064","https://openalex.org/W2993007949","https://openalex.org/W3103170042","https://openalex.org/W3161903544","https://openalex.org/W3177813494","https://openalex.org/W3184831477","https://openalex.org/W3211801722","https://openalex.org/W4245415816","https://openalex.org/W4254188649","https://openalex.org/W4284709233","https://openalex.org/W4286530324","https://openalex.org/W4286531991","https://openalex.org/W4324138978","https://openalex.org/W4389544179","https://openalex.org/W4402665833"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W2905433371","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W1993948687","https://openalex.org/W2888392564"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"Large":[3],"Language":[4],"Models":[5],"for":[6,122,187],"code":[7,24,91],"(LLMc)":[8],"have":[9],"transformed":[10],"the":[11,120,134,177],"landscape":[12],"of":[13,99,136],"software":[14,57],"engineering":[15],"(SE),":[16],"demonstrating":[17],"significant":[18],"efficacy":[19],"in":[20,56,90,111,146,189],"tasks":[21],"such":[22],"as":[23,73],"completion,":[25],"summarization,":[26],"review,":[27],"tracing,":[28],"translation,":[29],"test":[30],"case":[31],"generation,":[32],"clone":[33],"detection,":[34],"and":[35,42,53,81,107,113,162,191],"bug":[36],"fixing.":[37],"Notably,":[38],"GitHub":[39],"Copilot":[40],"[31]":[41],"Google's":[43],"CodeBot":[44],"[21]":[45],"exemplify":[46],"how":[47],"LLMc":[48,100,148,182],"contributes":[49],"to":[50,69,153,175],"substantial":[51],"time":[52],"effort":[54],"savings":[55],"development.":[58],"However,":[59],"despite":[60],"their":[61,185],"widespread":[62],"use,":[63],"there":[64],"is":[65,152],"a":[66,96,123,137,167],"growing":[67],"need":[68],"thoroughly":[70],"assess":[71],"LLMc,":[72,161],"current":[74],"evaluation":[75,125],"processes":[76],"heavily":[77],"rely":[78],"on":[79,86,170],"accuracy":[80],"robustness":[82],"metrics,":[83],"lacking":[84],"consensus":[85],"additional":[87],"influential":[88],"factors":[89],"generation.":[92],"This":[93,172],"gap":[94],"hinders":[95],"holistic":[97],"understanding":[98],"performance,":[101],"impacting":[102],"interpretability,":[103],"efficiency,":[104],"bias,":[105],"fairness,":[106],"robustness.":[108],"The":[109,150],"challenges":[110],"benchmarking":[112,138],"data":[114],"maintenance":[115],"compound":[116],"this":[117,131],"issue,":[118],"underscoring":[119],"necessity":[121],"comprehensive":[124],"approach.":[126],"To":[127],"address":[128],"these":[129],"issues,":[130],"dissertation":[132],"proposes":[133],"development":[135],"infrastructure,":[139],"named":[140],"HolBench,":[141],"aimed":[142],"at":[143],"overcoming":[144],"gaps":[145],"evaluating":[147],"quality.":[149],"goal":[151],"standardize":[154],"testing":[155],"scenarios,":[156],"facilitate":[157],"meaningful":[158],"comparisons":[159],"across":[160],"provide":[163],"multi-metric":[164],"measurements":[165],"beyond":[166],"sole":[168],"focus":[169],"accuracy.":[171],"approach":[173],"aims":[174],"decrease":[176],"costs":[178],"associated":[179],"with":[180],"advancing":[181],"research,":[183],"enhancing":[184],"reliability":[186],"adoption":[188],"academia":[190],"industry.":[192]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}