{"id":"W4386566659","doi":"10.18653/v1/2023.eacl-main.239","title":"DyLoRA: Parameter-Efficient Tuning of Pre-trained Models using Dynamic Search-Free Low-Rank Adaptation","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Benchmark (surveying); Rank (graph theory); Sorting; Language model; Range (aeronautics); Task (project management); Machine learning; Artificial intelligence; Algorithm","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":[0.001495658,0.003011403,0.001544336,0.0008862388,0.0005719183,0.001435565,0.003426533,0.002170043,0.006613118],"category_scores_gemma":[0.008303456,0.001278259,0.001500083,0.0007053734,0.000925112,0.002310017,0.002249299,0.005214023,0.005115551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009208658,"about_ca_system_score_gemma":0.001705913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01032128,"about_ca_topic_score_gemma":0.01884442,"domain_scores_codex":[0.9991139,0.0002464308,0.00006010387,0.000284135,0.0001654266,0.0001299681],"domain_scores_gemma":[0.998108,0.0009510937,0.0001156804,0.000396972,0.0003187093,0.0001095179],"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":[0.0003492856,0.0004437952,0.001821757,0.0002879524,0.0003060924,0.0002427126,0.0001628141,0.6368843,0.01448427,0.003033493,0.01995481,0.3220287],"study_design_scores_gemma":[0.00002794488,0.00003918752,0.0001153858,0.000008739716,0.00001392332,0.00002154242,0.00001488472,0.996086,0.001753501,0.001059462,0.000848291,0.00001114284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03283916,0.001304269,0.9330407,0.0004138367,0.0002210217,0.0001984249,0.0004367724,0.02817953,0.003366255],"genre_scores_gemma":[0.4884644,0.000545301,0.4931149,0.001370234,0.0001682949,0.0008012952,0.003538847,0.003845883,0.008150911],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01032128,"threshold_uncertainty_score":0.02212304,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07253695507708174,"score_gpt":0.29376392995067,"score_spread":0.2212269748735883,"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."}}