{"id":"W4382202851","doi":"10.1609/aaai.v37i11.26579","title":"Multi-Mask Label Mapping for Prompt-Based Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment","keywords":"Computer science; Natural language processing; Artificial intelligence; Task (project management); Context (archaeology); Exploit; Word (group theory); Machine learning; Linguistics","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":[0.002403992,0.001603916,0.001469565,0.0007800949,0.0009005016,0.001235779,0.003987594,0.003001964,0.004487358],"category_scores_gemma":[0.01115319,0.0006324361,0.0008863761,0.0007873507,0.001351212,0.004965818,0.003132741,0.003706167,0.002123814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023339,"about_ca_system_score_gemma":0.001540735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001479048,"about_ca_topic_score_gemma":0.002859751,"domain_scores_codex":[0.9983938,0.0005980635,0.00006870876,0.0005519769,0.0002677127,0.0001197846],"domain_scores_gemma":[0.9952878,0.002304937,0.0002664686,0.001206439,0.0005964495,0.0003378939],"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":[0.001335104,0.001035671,0.00346662,0.0003697133,0.00007048858,0.0003958524,0.0007750186,0.1116071,0.03354739,0.01601753,0.01188855,0.8194909],"study_design_scores_gemma":[0.00004926635,0.000314852,0.0003804709,0.00001693779,0.00002074536,0.0001198853,0.0001073921,0.9541438,0.012918,0.02905823,0.002837138,0.00003334494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03129755,0.0002705848,0.958932,0.0003758269,0.0001069089,0.0001498474,0.0001950721,0.007569248,0.001103006],"genre_scores_gemma":[0.5577006,0.000159398,0.432741,0.0007697555,0.0001496398,0.0004521215,0.001199304,0.000496053,0.00633209],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004487358,"threshold_uncertainty_score":0.01501173,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1923271154927747,"score_gpt":0.3382618546859622,"score_spread":0.1459347391931875,"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."}}