{"id":"W4401043913","doi":"10.18653/v1/2024.naacl-long.454","title":"Enhancing Argument Summarization: Prioritizing Exhaustiveness in Key Point Generation and Introducing an Automatic Coverage Evaluation Metric","year":2024,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Automatic summarization; Argument (complex analysis); Key (lock); Metric (unit); Computer science; Point (geometry); Engineering; Artificial intelligence; Computer security; Mathematics; Operations management","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006286803,0.001468767,0.001460601,0.005948029,0.0008969966,0.003961785,0.001909903,0.001749015,0.003331329],"category_scores_gemma":[0.04672682,0.0005935229,0.0006939906,0.003055669,0.000909952,0.005359835,0.002895469,0.001281591,0.001655343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009807523,"about_ca_system_score_gemma":0.001948379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002272107,"about_ca_topic_score_gemma":0.00412842,"domain_scores_codex":[0.9908686,0.003909071,0.0008973769,0.0009707644,0.002994349,0.0003599071],"domain_scores_gemma":[0.9600812,0.025571,0.00262039,0.002909341,0.00811155,0.0007065121],"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":[0.001035906,0.0004771344,0.009970592,0.001561339,0.0001888369,0.0003156044,0.00141611,0.02834071,0.04257091,0.01441051,0.01797178,0.8817406],"study_design_scores_gemma":[0.0002523388,0.0008223196,0.008581324,0.0004581269,0.000453903,0.0006048786,0.0009633861,0.8571154,0.07627285,0.0326185,0.02169587,0.0001610657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1233735,0.005090279,0.8499035,0.00119523,0.0002938388,0.0008097384,0.001677787,0.008192327,0.009463859],"genre_scores_gemma":[0.4790272,0.0008778351,0.5127627,0.0002014179,0.0001856529,0.0003626589,0.003362956,0.0009520818,0.002267463],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006286803,"threshold_uncertainty_score":0.03324819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02062459436336553,"score_gpt":0.3120638485940622,"score_spread":0.2914392542306967,"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."}}