{"id":"https://openalex.org/W7162285245","doi":"https://doi.org/10.1007/s10664-026-10823-5","title":"From brittle to robust: Improving LLM annotations for SE optimization","display_name":"From brittle to robust: Improving LLM annotations for SE optimization","publication_year":2026,"publication_date":"2026-05-25","ids":{"openalex":"https://openalex.org/W7162285245","doi":"https://doi.org/10.1007/s10664-026-10823-5"},"language":"en","primary_location":{"id":"doi:10.1007/s10664-026-10823-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-026-10823-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-026-10823-5.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10664-026-10823-5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115763930","display_name":"Lohith Senthilkumar","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lohith Senthilkumar","raw_affiliation_strings":["Computer Science, North Carolina State University, Oval Dr, Raleigh, NC, 27606, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science, North Carolina State University, Oval Dr, Raleigh, NC, 27606, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136974680","display_name":"Tim Menzies","orcid":"https://orcid.org/0000-0002-5040-3196"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tim Menzies","raw_affiliation_strings":["Computer Science, North Carolina State University, Oval Dr, Raleigh, NC, 27606, USA"],"raw_orcid":"https://orcid.org/0000-0002-5040-3196","affiliations":[{"raw_affiliation_string":"Computer Science, North Carolina State University, Oval Dr, Raleigh, NC, 27606, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5136974680"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":{"value":2890,"currency":"USD","value_usd":2890},"apc_paid":{"value":2890,"currency":"USD","value_usd":2890},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62436438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.28439998626708984,"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":0.28439998626708984,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.10589999705553055,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.08780000358819962,"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/ensemble-learning","display_name":"Ensemble learning","score":0.5763999819755554},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5453000068664551},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4950999915599823},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.48399999737739563},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.46149998903274536},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.41920000314712524},{"id":"https://openalex.org/keywords/crossover","display_name":"Crossover","score":0.4142000079154968},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.40720000863075256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7645999789237976},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5763999819755554},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5453000068664551},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5235999822616577},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48989999294281006},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.48399999737739563},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C122507166","wikidata":"https://www.wikidata.org/wiki/Q628906","display_name":"Crossover","level":2,"score":0.4142000079154968},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4032999873161316},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.3995000123977661},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30630001425743103},{"id":"https://openalex.org/C135945739","wikidata":"https://www.wikidata.org/wiki/Q1211457","display_name":"Software release life cycle","level":5,"score":0.2937000095844269},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.25130000710487366},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10664-026-10823-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-026-10823-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-026-10823-5.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10664-026-10823-5","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10664-026-10823-5","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10664-026-10823-5.pdf","source":{"id":"https://openalex.org/S109852484","display_name":"Empirical Software Engineering","issn_l":"1382-3256","issn":["1382-3256","1573-7616"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Empirical Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7162285245.pdf","grobid_xml":"https://content.openalex.org/works/W7162285245.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W125926453","https://openalex.org/W397180395","https://openalex.org/W1534477342","https://openalex.org/W1978813754","https://openalex.org/W1988790447","https://openalex.org/W2040915209","https://openalex.org/W2054723957","https://openalex.org/W2100064951","https://openalex.org/W2100712850","https://openalex.org/W2106535838","https://openalex.org/W2117897510","https://openalex.org/W2126819778","https://openalex.org/W2132938761","https://openalex.org/W2143381319","https://openalex.org/W2148076038","https://openalex.org/W2148854374","https://openalex.org/W2158242434","https://openalex.org/W2165038501","https://openalex.org/W2330210193","https://openalex.org/W2400753773","https://openalex.org/W2523330636","https://openalex.org/W2566040466","https://openalex.org/W2594132308","https://openalex.org/W2605705966","https://openalex.org/W2733078680","https://openalex.org/W2911964244","https://openalex.org/W2954122741","https://openalex.org/W2962911862","https://openalex.org/W2963715041","https://openalex.org/W2964298054","https://openalex.org/W3007313497","https://openalex.org/W3106889297","https://openalex.org/W3108032709","https://openalex.org/W3133702157","https://openalex.org/W3163661296","https://openalex.org/W4284665627","https://openalex.org/W4313547549","https://openalex.org/W4378591002","https://openalex.org/W4384302749","https://openalex.org/W4384345672","https://openalex.org/W4388483039","https://openalex.org/W4388539339","https://openalex.org/W4394769544","https://openalex.org/W4395036569","https://openalex.org/W4401508141","https://openalex.org/W4401863388","https://openalex.org/W4402665833","https://openalex.org/W4403122846","https://openalex.org/W4404059931","https://openalex.org/W4407026437","https://openalex.org/W4409541691","https://openalex.org/W4411272222","https://openalex.org/W7133186244"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Software":[1],"analytics":[2],"often":[3],"builds":[4],"from":[5,110],"labeled":[6,176],"data.":[7],"Labeling":[8],"can":[9,194],"be":[10,211],"slow,":[11],"error":[12],"prone,":[13],"and":[14,140,166,213,227],"expensive.":[15],"When":[16,74],"human":[17,181],"expertise":[18],"is":[19,53],"scarce,":[20],"SE":[21,126],"researchers":[22],"sometimes":[23],"ask":[24],"large":[25],"language":[26],"models":[27],"(LLMs)":[28],"for":[29,56],"the":[30],"missing":[31],"labels.":[32],"While":[33],"this":[34,63],"has":[35,47,121],"been":[36,122],"successful":[37,206],"in":[38,163],"some":[39],"domains,":[40],"recent":[41],"results":[42,109,209],"show":[43],"that":[44,147,188,204],"LLM-based":[45],"labeling":[46,52],"blind":[48],"spots.":[49],"Specifically,":[50],"their":[51],"not":[54],"effective":[55],"higher":[57],"dimensional":[58,198],"multi-objective":[59,127,199],"problems.":[60],"To":[61,220],"address":[62],"task,":[64],"we":[65,186,202],"propose":[66],"a":[67],"novel":[68],"LLM":[69],"prompting":[70,208],"strategy":[71],"called":[72],"SynthCore.":[73],"one":[75],"opinion":[76],"fails,":[77],"SynthCore\u2019s":[78,143,217],"combines":[79],"multiple":[80,111],"separated":[81],"opinions":[82],"generated":[83],"by":[84,177],"LLMs":[85],"(with":[86,115],"no":[87,116],"knowledge":[88],"of":[89,96,158,190],"each":[90],"others\u2019":[91],"answers)":[92],"into":[93],"an":[94],"ensemble":[95,144,218],"few-shot":[97,207],"learners.":[98],"Simpler":[99],"than":[100,150],"other":[101,205],"strategies":[102],"(e.g.":[103],"chain-of-thought,":[104],"multi-agent-debate,":[105],"etc)":[106],"SynthCore":[107,120],"aggregates":[108],"single":[112],"prompt":[113],"sessions":[114],"crossover":[117],"between":[118],"them).":[119],"tested":[123],"on":[124],"49":[125],"optimization":[128],"tasks,":[129],"handling":[130],"tasks":[131],"as":[132,134],"diverse":[133],"software":[135],"project":[136],"management,":[137],"Makefile":[138],"configuration,":[139],"hyperparameter":[141],"optimization.":[142],"found":[145],"optimizations":[146,171],"are":[148,229],"better":[149],"state-of-the-art":[151],"alternative":[152],"approaches":[153],"(Gaussian":[154],"Process":[155],"Models,":[156],"Tree":[157],"Parzen":[159],"Estimators,":[160],"active":[161],"learners":[162,193],"both":[164],"exploration":[165],"exploitation":[167],"mode).":[168],"Importantly,":[169],"these":[170,184],"were":[172],"made":[173],"using":[174,216],"data":[175,226],"LLMs,":[178],"without":[179],"any":[180],"opinions.":[182],"From":[183],"experiments,":[185],"conclude":[187],"ensembles":[189],"few":[191],"shot":[192],"successfully":[195],"annotate":[196],"high":[197],"tasks.":[200],"Further,":[201],"speculate":[203],"could":[210],"quickly":[212],"easily":[214],"enhanced":[215],"approach.":[219],"support":[221],"open":[222],"science,":[223],"all":[224],"our":[225],"scripts":[228],"available":[230],"at":[231],"https://github.com/lohithsowmiyan/lazy-llm/tree/clusters":[232],".":[233]},"counts_by_year":[],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2026-05-26T00:00:00"}