{"id":"W4385570165","doi":"10.18653/v1/2023.findings-acl.206","title":"Two Examples are Better than One: Context Regularization for Gradient-based Prompt Tuning","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Regularization (linguistics); Context (archaeology); Machine learning; Artificial intelligence; Language model","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":[0.0002736634,0.00009671778,0.0001202668,0.0001253241,0.0001379935,0.0001415385,0.0004081036,0.00003551997,0.000009751689],"category_scores_gemma":[0.0000523109,0.00009096415,0.00005178462,0.0002915859,0.0000159507,0.0002451192,0.0001033861,0.00005053265,0.00002657843],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002684307,"about_ca_system_score_gemma":0.00003454271,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000566854,"about_ca_topic_score_gemma":0.0001048094,"domain_scores_codex":[0.9989568,0.00003351083,0.0001785194,0.0003710735,0.0001901626,0.0002699134],"domain_scores_gemma":[0.9992419,0.0001119412,0.00007344455,0.0004358007,0.00008274057,0.00005421319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001971475,0.0001188361,0.03198716,0.0002132227,0.00006445176,0.00001552488,0.002610089,0.009085938,0.01147258,0.7393863,0.003739323,0.2012868],"study_design_scores_gemma":[0.0006095374,0.00003220284,0.003696504,0.00005797189,0.000005022931,7.55802e-7,0.00009575955,0.9777201,0.005231219,0.01093686,0.001447689,0.000166375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07056548,0.000009921981,0.924158,0.003992429,0.0002099986,0.0003274991,0.00000221745,0.0004963258,0.0002380871],"genre_scores_gemma":[0.8319196,4.200811e-7,0.1658359,0.0009985885,0.0000929359,0.00007618688,0.00002305825,0.00001249255,0.00104085],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9686342,"threshold_uncertainty_score":0.370941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06752832518457182,"score_gpt":0.2678553627134493,"score_spread":0.2003270375288775,"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."}}