{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000977524,0.00006096585,0.0000982178,0.00007793278,0.00004054138,0.00004740589,0.001527113,0.00001782975,0.000001378004],"category_scores_gemma":[0.00009468632,0.00004643478,0.000008550689,0.0003533618,0.00001444114,0.0004325197,0.001090816,0.00002922232,0.000004686467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001085059,"about_ca_system_score_gemma":0.00003581444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003894393,"about_ca_topic_score_gemma":0.000005700843,"domain_scores_codex":[0.9990436,0.00005597147,0.0001268039,0.0004643417,0.0001737753,0.0001355099],"domain_scores_gemma":[0.9972981,0.0007448228,0.00004916765,0.001835913,0.00004745791,0.00002456716],"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":[0.000483076,0.0005823605,0.006239878,0.002177728,0.0004424846,0.00002673524,0.002255903,0.3415065,0.03711476,0.09220497,0.002215569,0.5147501],"study_design_scores_gemma":[0.0005158431,0.00004952246,0.001643196,0.0000573567,0.000008720397,0.000001080552,0.00002817344,0.9950197,0.00235977,0.0001830031,0.00006885485,0.00006479922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1273977,0.000005820847,0.8719532,0.00008053322,0.00008380171,0.000288483,0.00002468595,0.0001122055,0.00005362387],"genre_scores_gemma":[0.7335109,8.625173e-7,0.2661283,0.00001907487,0.000009657987,0.0000134159,0.000287758,0.000005266406,0.00002471743],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6535133,"threshold_uncertainty_score":0.2837781,"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."}}