{"id":"https://openalex.org/W7167606328","doi":"https://doi.org/10.1145/3786181.3788728","title":"Benchmarking LLM Commit Message Generation through a Developer-centric Pairwise Preference Framework","display_name":"Benchmarking LLM Commit Message Generation through a Developer-centric Pairwise Preference Framework","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7167606328","doi":"https://doi.org/10.1145/3786181.3788728"},"language":null,"primary_location":{"id":"doi:10.1145/3786181.3788728","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788728","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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786181.3788728","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140167598","display_name":"Lucas Aguiar","orcid":"https://orcid.org/0009-0002-2405-046X"},"institutions":[{"id":"https://openalex.org/I102939073","display_name":"Universidade Estadual do Cear\u00e1","ror":"https://ror.org/00sec1m50","country_code":"BR","type":"education","lineage":["https://openalex.org/I102939073"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas Aguiar","raw_affiliation_strings":["State University of Ceara, Fortaleza, Ceara, Brazil"],"raw_orcid":"https://orcid.org/0009-0002-2405-046X","affiliations":[{"raw_affiliation_string":"State University of Ceara, Fortaleza, Ceara, Brazil","institution_ids":["https://openalex.org/I102939073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140195217","display_name":"Matheus Freitas","orcid":"https://orcid.org/0009-0007-6980-5834"},"institutions":[{"id":"https://openalex.org/I102939073","display_name":"Universidade Estadual do Cear\u00e1","ror":"https://ror.org/00sec1m50","country_code":"BR","type":"education","lineage":["https://openalex.org/I102939073"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Matheus Freitas","raw_affiliation_strings":["State University of Ceara, Fortaleza, Ceara, Brazil"],"raw_orcid":"https://orcid.org/0009-0007-6980-5834","affiliations":[{"raw_affiliation_string":"State University of Ceara, Fortaleza, Ceara, Brazil","institution_ids":["https://openalex.org/I102939073"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065650493","display_name":"Matheus Paix\u00e3o","orcid":"https://orcid.org/0000-0002-1775-7259"},"institutions":[{"id":"https://openalex.org/I102939073","display_name":"Universidade Estadual do Cear\u00e1","ror":"https://ror.org/00sec1m50","country_code":"BR","type":"education","lineage":["https://openalex.org/I102939073"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Matheus Paixao","raw_affiliation_strings":["State University of Ceara, Fortaleza, Ceara, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-1775-7259","affiliations":[{"raw_affiliation_string":"State University of Ceara, Fortaleza, Ceara, Brazil","institution_ids":["https://openalex.org/I102939073"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024632348","display_name":"Rafael Augusto Ferreira do Carmo","orcid":"https://orcid.org/0000-0002-5080-1688"},"institutions":[{"id":"https://openalex.org/I243754102","display_name":"Universidade Federal do Cear\u00e1","ror":"https://ror.org/03srtnf24","country_code":"BR","type":"education","lineage":["https://openalex.org/I243754102"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rafael Carmo","raw_affiliation_strings":["Federal University of Ceara, Fortaleza, Ceara, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-5080-1688","affiliations":[{"raw_affiliation_string":"Federal University of Ceara, Fortaleza, Ceara, Brazil","institution_ids":["https://openalex.org/I243754102"]}]}],"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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.94675018,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"105","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9912999868392944,"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":0.9912999868392944,"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":0.00419999985024333,"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.0005000000237487257,"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/commit","display_name":"Commit","score":0.9799000024795532},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.8084999918937683},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6353999972343445},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4625999927520752},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.40230000019073486},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.35749998688697815}],"concepts":[{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.9799000024795532},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8295000195503235},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8084999918937683},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6353999972343445},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4625999927520752},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.40230000019073486},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.35749998688697815},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30970001220703125},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.30640000104904175},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28870001435279846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.26190000772476196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786181.3788728","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788728","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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3786181.3788728","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786181.3788728","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 3rd International Workshop on Large Language Models For Code","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.4160645604133606,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1970407057","https://openalex.org/W1989479444","https://openalex.org/W1997405881","https://openalex.org/W2013784666","https://openalex.org/W2057049321","https://openalex.org/W2060457651","https://openalex.org/W2133333349","https://openalex.org/W2164519300","https://openalex.org/W2741561716","https://openalex.org/W2888312537","https://openalex.org/W2964772344","https://openalex.org/W3099130275","https://openalex.org/W3123545166","https://openalex.org/W3193171773","https://openalex.org/W4220877452","https://openalex.org/W4284708426","https://openalex.org/W4384302768","https://openalex.org/W4391741735","https://openalex.org/W4400583028","https://openalex.org/W4403194077","https://openalex.org/W7125639500"],"related_works":[],"abstract_inverted_index":{"Commit":[0],"Messages":[1],"are":[2,246],"crucial":[3],"for":[4,248],"software":[5,24],"maintenance,":[6],"as":[7,11,19,90,111,242],"they":[8],"serve":[9],"both":[10],"a":[12,20,64,96,100,168,203],"means":[13],"of":[14,225,252],"communication":[15],"between":[16,171],"developers":[17,47,109,150,177],"and":[18,33,80,92,151,162,174],"way":[21],"to":[22,45,99,104],"document":[23],"evolution.":[25],"However,":[26,59],"writing":[27],"good":[28,52],"commit":[29,57,72,130,146],"messages":[30,73,147,209,230],"is":[31],"time-consuming":[32],"non-trivial.":[34],"Solutions":[35],"that":[36,70,108,128,218,238],"employ":[37],"Large":[38,253],"Language":[39,254],"Models":[40,255],"(LLMs)":[41,256],"have":[42],"been":[43],"proposed":[44],"assist":[46],"in":[48,54,74,78,231,257],"this":[49,115],"task,":[50],"demonstrating":[51],"performance":[53],"automatically":[55],"generating":[56],"messages.":[58,84],"benchmarking":[60,251],"these":[61],"models":[62],"remains":[63],"significant":[65,169],"challenge.":[66],"Research":[67],"has":[68],"demonstrated":[69],"developer-written":[71,101],"literature":[75],"datasets":[76],"vary":[77],"quality":[79,107,131],"often":[81],"contain":[82],"low-quality":[83],"Furthermore,":[85],"traditional":[86,175,183],"evaluation":[87,120],"metrics,":[88],"such":[89,241],"BLEU":[91],"ROUGE,":[93],"which":[94],"compare":[95],"generated":[97,210],"message":[98],"message,":[102],"fail":[103],"capture":[105],"the":[106,124,179,186,207,226],"perceive":[110],"important.":[112],"To":[113],"address":[114],"gap,":[116],"we":[117,144],"propose":[118],"an":[119],"framework":[121],"based":[122],"on":[123],"Elo":[125,192],"Rating":[126],"system":[127],"measures":[129],"through":[132],"direct":[133],"pairwise":[134],"comparisons,":[135],"reflecting":[136],"genuine":[137],"developer":[138,172,229],"preferences.":[139],"In":[140],"our":[141,243],"empirical":[142],"study,":[143],"evaluated":[145],"written":[148],"by":[149,211],"also":[152,216],"three":[153],"automated":[154],"solutions:":[155],"OMG":[156,212,219],"(LLM-based),":[157],"FIRA":[158],"(traditional":[159],"Neural":[160,187],"Network-based),":[161],"NNGen":[163],"(Retrieval-Based).":[164],"Our":[165,235],"analysis":[166],"revealed":[167],"misalignment":[170],"preferences":[173],"metrics:":[176],"preferred":[178,222],"LLM-based":[180],"solution,":[181],"while":[182],"metrics":[184],"favored":[185],"Network":[188],"solution":[189],"(RQ1).":[190],"The":[191],"scores":[193],"offered":[194],"valuable":[195],"insights":[196],"into":[197],"developers\u2019":[198],"preferences,":[199],"revealing":[200],"not":[201],"only":[202],"strong":[204],"inclination":[205],"towards":[206],"detailed":[208],"over":[213,223],"developers\u2019,":[214],"but":[215],"predicting":[217],"would":[220],"be":[221],"80%":[224],"time":[227],"against":[228],"certain":[232],"criteria":[233],"(RQ2).":[234],"findings":[236],"indicate":[237],"developer-centric":[239],"frameworks,":[240],"Elo-based":[244],"approach,":[245],"essential":[247],"more":[249],"accurate":[250],"code-related":[258],"tasks.":[259]},"counts_by_year":[],"updated_date":"2026-07-08T06:22:20.291053","created_date":"2026-07-08T00:00:00"}