{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005864269,0.0001802438,0.0002036072,0.0002649336,0.0003243968,0.0002786772,0.002000248,0.00009868916,0.00001313464],"category_scores_gemma":[0.0009702646,0.0001396308,0.0001000256,0.00126606,0.0001940694,0.0003220845,0.0003256899,0.0002459625,0.0001373416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003670528,"about_ca_system_score_gemma":0.00008537223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006295232,"about_ca_topic_score_gemma":0.000001878777,"domain_scores_codex":[0.9983854,0.00001020401,0.0004248776,0.0004785738,0.000331511,0.000369397],"domain_scores_gemma":[0.9987059,0.0001496067,0.0003562976,0.000274202,0.0004671644,0.00004689495],"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":[0.00001985743,0.0001081982,0.0003968488,0.00007352163,0.0000100572,1.718603e-7,0.0007876732,0.0001530275,0.1487088,0.7117634,0.0003391272,0.1376393],"study_design_scores_gemma":[0.00005510998,0.0001332543,0.0002833953,0.0001233855,0.000004092329,3.379106e-7,0.0007649089,0.4958277,0.4417852,0.05993311,0.0009166849,0.0001728472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.14582,0.00002768993,0.8190928,0.02764758,0.0007992774,0.001903546,0.000008868757,0.002615192,0.002085041],"genre_scores_gemma":[0.9622319,0.00001438948,0.0365118,0.0001031326,0.00002315533,0.0001804654,0.000001292751,0.00001259712,0.0009213205],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8164118,"threshold_uncertainty_score":0.5693977,"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."}}