{"id":"https://openalex.org/W7128767648","doi":"https://doi.org/10.1145/3770762.3772576","title":"Fine-Tuning Open-Source Models as a Viable Alternative to Proprietary LLMs for Explaining Compiler Messages","display_name":"Fine-Tuning Open-Source Models as a Viable Alternative to Proprietary LLMs for Explaining Compiler Messages","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7128767648","doi":"https://doi.org/10.1145/3770762.3772576"},"language":"en","primary_location":{"id":"doi:10.1145/3770762.3772576","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770762.3772576","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 57th ACM Technical Symposium on Computer Science Education V.1","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3770762.3772576","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094166387","display_name":"Lorenzo Lee Solano","orcid":"https://orcid.org/0009-0002-6079-1265"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Lorenzo Lee Solano","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0009-0002-6079-1265","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011660743","display_name":"Charles Koutcheme","orcid":"https://orcid.org/0000-0002-2272-2763"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Charles Koutcheme","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0002-2272-2763","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041367899","display_name":"Juho Leinonen","orcid":"https://orcid.org/0000-0001-6829-9449"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Juho Leinonen","raw_affiliation_strings":["Aalto University, Espoo, Finland"],"raw_orcid":"https://orcid.org/0000-0001-6829-9449","affiliations":[{"raw_affiliation_string":"Aalto University, Espoo, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064437426","display_name":"Alexandra Vassar","orcid":null},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alexandra Vassar","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0001-8856-2566","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053777629","display_name":"J. Renzella","orcid":"https://orcid.org/0000-0002-9587-1196"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jake Renzella","raw_affiliation_strings":["University of New South Wales, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0002-9587-1196","affiliations":[{"raw_affiliation_string":"University of New South Wales, Sydney, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":2,"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":0.13065628,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"617","last_page":"623"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.2919999957084656,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10533","display_name":"Teaching and Learning Programming","score":0.2919999957084656,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.1387999951839447,"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/T10260","display_name":"Software Engineering Research","score":0.08470000326633453,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.8952000141143799},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3959999978542328},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.3790000081062317},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.34610000252723694},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.33169999718666077},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.31610000133514404}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.8952000141143799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8198999762535095},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4772999882698059},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.40529999136924744},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.390500009059906},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3370000123977661},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.33169999718666077},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3770762.3772576","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770762.3772576","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 57th ACM Technical Symposium on Computer Science Education V.1","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/143267","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/9aa0317b-7d1e-4e7c-a633-b54c1416a356","pdf_url":null,"source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"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":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1145/3770762.3772576","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3770762.3772576","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 57th ACM Technical Symposium on Computer Science Education V.1","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.736068844795227,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1996290308","https://openalex.org/W2117968587","https://openalex.org/W3163358064","https://openalex.org/W4283705032","https://openalex.org/W4323033692","https://openalex.org/W4380353816","https://openalex.org/W4382654294","https://openalex.org/W4383092673","https://openalex.org/W4388850769","https://openalex.org/W4390621416","https://openalex.org/W4390621504","https://openalex.org/W4390985631","https://openalex.org/W4391584331","https://openalex.org/W4392564649","https://openalex.org/W4392564798","https://openalex.org/W4400208028","https://openalex.org/W4400267611","https://openalex.org/W4401357303","https://openalex.org/W4404091256","https://openalex.org/W4406803762","https://openalex.org/W4407681796","https://openalex.org/W4407770947","https://openalex.org/W4407771325"],"related_works":[],"abstract_inverted_index":{"Cryptic":[0],"compiler":[1,67,89],"error":[2,29],"messages":[3],"continue":[4],"to":[5,69,91,197],"present":[6],"a":[7,78,105,114,180,190],"significant":[8],"barrier":[9],"for":[10,35,43,183,193],"novice":[11],"programmers,":[12],"especially":[13,204],"in":[14,46,71,140,147],"foundational":[15],"languages":[16],"like":[17],"C.":[18],"Although":[19],"large":[20],"language":[21],"models":[22,63,125,175],"(LLMs)":[23],"can":[24,56],"generate":[25],"accurate":[26],"and":[27,37,98,113,137,158,160],"comprehensible":[28],"explanations,":[30],"their":[31,41],"computational":[32],"requirements,":[33],"propensity":[34],"over-assistance,":[36],"privacy":[38],"concerns":[39],"constrain":[40],"suitability":[42],"widespread":[44],"adoption":[45],"educational":[47,202],"tools.":[48,187],"This":[49],"work":[50],"investigates":[51],"how":[52],"Supervised":[53],"Fine-Tuning":[54],"(SFT)":[55],"enhance":[57],"the":[58,148,153],"performance":[59,101],"of":[60,81,118,124],"smaller,":[61,206],"open-source":[62,94,142],"when":[64],"explaining":[65],"C":[66,88],"errors":[68,90],"students":[70],"introductory":[72],"programming":[73],"courses":[74],"(CS1/2).":[75],"We":[76,151,188],"derive":[77],"training":[79],"dataset":[80],"40,000":[82],"input-output":[83],"pairs":[84],"from":[85],"CS1/2":[86],"student":[87],"fine-tune":[92],"three":[93],"models:":[95],"Qwen3-4B,":[96],"Llama-3.1-8B,":[97],"Qwen3-32B.":[99],"Model":[100],"was":[102],"assessed":[103],"through":[104],"dual":[106],"evaluation":[107],"framework":[108],"involving":[109],"expert":[110,136],"human":[111],"reviewers":[112],"large-scale":[115],"automated":[116],"analysis":[117],"8,000":[119],"responses":[120],"using":[121],"an":[122],"ensemble":[123],"as":[126],"judges.":[127],"Our":[128,169],"results":[129],"indicate":[130],"that":[131,172],"SFT":[132],"significantly":[133],"improves":[134],"both":[135],"LLM-as-judge":[138,162],"ratings":[139],"smaller":[141,174],"models,":[143],"with":[144,167,205],"reduced":[145],"gains":[146],"larger":[149],"model.":[150],"analyse":[152],"trade-offs":[154],"between":[155],"model":[156],"size":[157],"quality,":[159],"validate":[161],"by":[163],"demonstrating":[164],"inter-rater":[165],"agreement":[166],"experts.":[168],"findings":[170],"demonstrate":[171],"fine-tuning":[173],"on":[176],"high-quality":[177],"data":[178],"is":[179],"viable":[181],"strategy":[182],"creating":[184],"specialised":[185],"pedagogical":[186],"provide":[189],"replicable":[191],"methodology":[192],"enabling":[194],"broader":[195],"access":[196],"advanced":[198],"AI":[199],"capabilities":[200],"within":[201],"contexts,":[203],"economical":[207],"models.":[208]},"counts_by_year":[],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2026-02-14T00:00:00"}