{"id":"W4405194255","doi":"10.5753/stil.2024.245416","title":"Toxic Text Classification in Portuguese: Is LLaMA 3.1 8B All You Need?","year":2024,"lang":"en","type":"article","venue":"","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Blutip (Canada)","funders":"Universidade Federal de Ouro Preto; Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Portuguese; Computer science; Natural language processing; Artificial intelligence; 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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002797753,0.0001095807,0.00008988994,0.0002369585,0.00003270601,0.0002551147,0.0003597799,0.00008808157,0.0002100822],"category_scores_gemma":[0.00001475079,0.0000961109,0.00005265697,0.0007412665,0.00001597279,0.0004880547,0.00007398104,0.0001618241,0.001252805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007678568,"about_ca_system_score_gemma":0.00006451313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001304928,"about_ca_topic_score_gemma":0.00004855528,"domain_scores_codex":[0.998859,0.00003031108,0.0002144125,0.00042626,0.0002242886,0.0002456839],"domain_scores_gemma":[0.9994388,0.00002884303,0.00002390212,0.0004032311,0.00002831471,0.00007687178],"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":[0.000004886952,0.00007333053,0.0002937608,0.0000372227,0.00002166476,0.0000938438,0.001486275,0.00001807376,0.02833182,0.0756655,0.03072874,0.8632449],"study_design_scores_gemma":[0.0004273315,0.0002429083,0.01792495,0.00012635,0.00001319486,0.0001393344,0.0003600949,0.5116867,0.05974702,0.0103118,0.398323,0.0006973763],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2246737,0.002198059,0.5334752,0.03953914,0.004028384,0.0007115639,0.000004353229,0.002922521,0.1924471],"genre_scores_gemma":[0.9758763,0.0001202762,0.00605865,0.001011055,0.0001107469,0.00002068301,0.000004506373,0.00001210861,0.01678569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8625475,"threshold_uncertainty_score":0.9995248,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02507409172674729,"score_gpt":0.2668513962956643,"score_spread":0.2417773045689171,"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."}}