{"id":"W4401043207","doi":"10.18653/v1/2024.semeval-1.90","title":"OtterlyObsessedWithSemantics at SemEval-2024 Task 4: Developing a Hierarchical Multi-Label Classification Head for Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Bayerische Akademie der Wissenschaften","keywords":"SemEval; Computer science; Task (project management); Head (geology); Natural language processing; Artificial intelligence; Engineering; Biology","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":[0.005343375,0.00349945,0.001429889,0.001912368,0.002145059,0.004175652,0.002767336,0.003027549,0.02405067],"category_scores_gemma":[0.01176514,0.0008929597,0.001840978,0.0009837169,0.0009464831,0.006237749,0.004995866,0.004266463,0.01475953],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002332893,"about_ca_system_score_gemma":0.002417497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01171304,"about_ca_topic_score_gemma":0.02219879,"domain_scores_codex":[0.995789,0.00173504,0.0002136538,0.001196953,0.0006755757,0.0003898306],"domain_scores_gemma":[0.9951054,0.001790719,0.0001974633,0.00161018,0.0009408264,0.0003553655],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001216724,0.001081042,0.01032275,0.0008401798,0.0003695749,0.0005545729,0.001265564,0.01941184,0.01895974,0.009995072,0.2641648,0.6718181],"study_design_scores_gemma":[0.0003758618,0.0006763605,0.01129949,0.0003209457,0.0001900953,0.000624819,0.001847674,0.5919763,0.09483568,0.03800231,0.2596127,0.0002376574],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2764513,0.00329553,0.4592685,0.007395457,0.003604499,0.002302153,0.03748712,0.1392745,0.07092092],"genre_scores_gemma":[0.5533009,0.0003679209,0.312835,0.001471793,0.0003296421,0.001622521,0.06622392,0.003894725,0.05995356],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02405067,"threshold_uncertainty_score":0.08045757,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06040173108412855,"score_gpt":0.3564111599994934,"score_spread":0.2960094289153649,"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."}}