{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001953647,0.000137006,0.0001734512,0.0007547237,0.00009591955,0.0005509399,0.0001763519,0.00004843914,0.00002273922],"category_scores_gemma":[0.0001746461,0.0001323114,0.00002588678,0.001582166,0.00001238195,0.002408215,0.0001324868,0.0001082355,0.000004211412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004451384,"about_ca_system_score_gemma":0.00009858124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005206406,"about_ca_topic_score_gemma":0.0001819533,"domain_scores_codex":[0.9982408,0.0001840998,0.0003832267,0.0005969995,0.0004190598,0.0001758407],"domain_scores_gemma":[0.9993197,0.0001029896,0.00006420529,0.0003373454,0.0001271259,0.00004868659],"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":[0.000001382706,0.00006969274,0.0009735634,0.0001279805,0.00003137127,0.00002150289,0.002729795,0.01565992,0.130777,0.04800265,0.00002296695,0.8015822],"study_design_scores_gemma":[0.0001091038,0.00004165815,0.002041663,0.00008828846,0.00002089424,0.000007497063,0.00003748203,0.9463562,0.04533511,0.005782547,0.00002547412,0.0001540842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1647442,0.0003882621,0.8337433,0.0001828658,0.0001272409,0.0003061977,2.257393e-7,0.0003665545,0.0001411297],"genre_scores_gemma":[0.8071696,0.00005157519,0.1925442,0.00005100841,0.00008422307,0.00005053877,0.00001421971,0.000009007162,0.00002557559],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9306962,"threshold_uncertainty_score":0.5395502,"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."}}