{"id":"W4401042968","doi":"10.18653/v1/2024.semeval-1.164","title":"PetKaz at SemEval-2024 Task 3: Advancing Emotion Classification with an LLM for Emotion-Cause Pair Extraction in Conversations","year":2024,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"SemEval; Task (project management); Computer science; Natural language processing; Artificial intelligence; Extraction (chemistry); Emotion detection; Speech recognition; Emotion recognition; Chromatography; Engineering","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":[0.004917699,0.004457501,0.001541849,0.001836793,0.001489239,0.0037161,0.002275432,0.003413423,0.02255292],"category_scores_gemma":[0.01170199,0.0006541512,0.002531433,0.000790885,0.0006260044,0.003231609,0.004544509,0.00375362,0.02244961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00127831,"about_ca_system_score_gemma":0.001647185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006538274,"about_ca_topic_score_gemma":0.01086422,"domain_scores_codex":[0.9963814,0.001411359,0.0001456968,0.001043712,0.000614178,0.0004035459],"domain_scores_gemma":[0.9964446,0.001361792,0.0001197609,0.0007886596,0.0009274721,0.0003576783],"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":[0.002005498,0.0007474292,0.004887213,0.001128092,0.0005631194,0.000685909,0.0008229715,0.01334396,0.04187397,0.004189592,0.4549071,0.4748452],"study_design_scores_gemma":[0.0007502874,0.00112183,0.01509628,0.0002624101,0.0003818395,0.001369297,0.001153503,0.6963119,0.07456861,0.02019227,0.1884768,0.0003150706],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1766034,0.006400274,0.4884029,0.005375158,0.008197852,0.002441703,0.07316368,0.1951281,0.04428692],"genre_scores_gemma":[0.3651848,0.0008002135,0.4407564,0.001931484,0.001227597,0.002035298,0.1414512,0.0102612,0.03635171],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02255292,"threshold_uncertainty_score":0.07544696,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04026484820025493,"score_gpt":0.3169309115703094,"score_spread":0.2766660633700544,"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."}}