{"id":"W4406688098","doi":"10.1145/3714461","title":"Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Code generation; Code (set theory); Programming language; Software engineering; Key (lock); Operating system; Set (abstract data type)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001752739,0.001664156,0.0008798523,0.0008293414,0.000416937,0.001500137,0.00251612,0.001313588,0.003332289],"category_scores_gemma":[0.01583053,0.0007355917,0.001206281,0.000756048,0.0008858412,0.002860836,0.00190768,0.002936292,0.002328171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000963216,"about_ca_system_score_gemma":0.001817291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005018904,"about_ca_topic_score_gemma":0.01214848,"domain_scores_codex":[0.9987362,0.0004568094,0.00009652996,0.0003672533,0.0002343459,0.000108886],"domain_scores_gemma":[0.9957652,0.002830042,0.000196191,0.000799285,0.00029652,0.0001127371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003742634,0.0003895503,0.005567059,0.0007574429,0.0001892885,0.0002879374,0.0005838015,0.4956097,0.02405798,0.01034545,0.0109187,0.4509189],"study_design_scores_gemma":[0.00006119341,0.00006936251,0.0002462233,0.00003241009,0.00002515733,0.00006073649,0.00007670412,0.9784138,0.005627974,0.01180447,0.003563535,0.00001847408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0520844,0.001887479,0.9171027,0.0006337045,0.0001453796,0.0002794612,0.000691865,0.02379647,0.003378592],"genre_scores_gemma":[0.5033743,0.000656407,0.487383,0.0008115688,0.00007192721,0.0006674774,0.002100272,0.002984395,0.00195064],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005018904,"threshold_uncertainty_score":0.01114762,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.136645660242652,"score_gpt":0.3367384357981753,"score_spread":0.2000927755555234,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}