{"id":"W4385572414","doi":"10.18653/v1/2023.repl4nlp-1.19","title":"Effectiveness of Data Augmentation for Parameter Efficient Tuning with Limited Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Ottawa; Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Fine-tuning; Context (archaeology); Sentence; Language model; Task (project management); Function (biology); Simple (philosophy); Machine learning; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004884036,0.00167131,0.001038735,0.0006711151,0.0005591222,0.001595925,0.001673891,0.001429147,0.002361064],"category_scores_gemma":[0.03141318,0.0006323614,0.0008525581,0.0007495646,0.001080939,0.003734013,0.0024874,0.003238996,0.001588415],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005020107,"about_ca_system_score_gemma":0.001338386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002001007,"about_ca_topic_score_gemma":0.002996929,"domain_scores_codex":[0.9970251,0.001502466,0.0002159672,0.0007248061,0.0003799633,0.0001516774],"domain_scores_gemma":[0.9914703,0.005168497,0.0002972027,0.002377013,0.0005213116,0.0001655817],"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":[0.001343384,0.0008401363,0.009182845,0.0006257324,0.0004142237,0.0003011513,0.000595151,0.4153081,0.04063554,0.008417155,0.008647171,0.5136893],"study_design_scores_gemma":[0.0001010383,0.0002890983,0.001495778,0.00007801729,0.00006897764,0.000139027,0.000140126,0.9588133,0.02133407,0.01227629,0.005207799,0.00005666117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1912746,0.002185206,0.7863676,0.00135046,0.0003918006,0.0003092292,0.001057869,0.01159962,0.005463586],"genre_scores_gemma":[0.7551695,0.0004304309,0.2383227,0.0006242158,0.0001158631,0.0005046958,0.002127273,0.0007406485,0.001964699],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004884036,"threshold_uncertainty_score":0.02582955,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1505365060439821,"score_gpt":0.3475230354588228,"score_spread":0.1969865294148407,"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."}}