{"id":"W4412496985","doi":"10.36227/techrxiv.175303890.08902658/v1","title":"A Comprehensive Survey of Parameter-Efficient Fine-Tuning for Large Language and Vision Models","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004905055,0.0002391102,0.0004941487,0.0002004731,0.00006420843,0.00009294129,0.0006647828,0.0001690138,0.00000181555],"category_scores_gemma":[0.0002185387,0.0002085766,0.0001060292,0.0002396312,0.00003575799,0.0001445104,0.002492866,0.0002431325,2.853112e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002603434,"about_ca_system_score_gemma":0.00009209806,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002688045,"about_ca_topic_score_gemma":0.00002834003,"domain_scores_codex":[0.9984267,0.000114853,0.0003756199,0.0006352644,0.0001926762,0.0002548548],"domain_scores_gemma":[0.9975221,0.0009707277,0.0002124853,0.0007702908,0.0004689641,0.00005540571],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005961411,0.001738014,0.0009462346,0.0086456,0.0005401503,0.00005833568,0.01105448,0.04084191,0.01250792,0.1667718,0.006448565,0.7498508],"study_design_scores_gemma":[0.0003244769,0.0001370162,0.0005144709,0.0003313356,0.00001102501,0.00000119025,0.00003509843,0.9714145,0.0157863,0.01098743,0.0002065277,0.0002506034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01183498,0.001447411,0.9849775,0.00004960565,0.0001229036,0.0007893656,0.000261405,0.0002077433,0.0003090966],"genre_scores_gemma":[0.5177208,0.0001256668,0.4815423,0.0001522474,0.000009979824,0.00005102774,0.00007008397,0.00001088874,0.0003170088],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9305726,"threshold_uncertainty_score":0.8505507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0540474335713086,"score_gpt":0.3739768597857634,"score_spread":0.3199294262144548,"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."}}