{"id":"W4402715036","doi":"10.18653/v1/2024.sigdial-1.26","title":"Coherence-based Dialogue Discourse Structure Extraction using Open-Source Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Computer science; Coherence (philosophical gambling strategy); Natural language processing; Artificial intelligence; Extraction (chemistry); Linguistics; Physics; Philosophy; Chemistry","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":[0.001997099,0.001858034,0.0007567526,0.003639282,0.001113766,0.001885124,0.001289347,0.00108852,0.003489337],"category_scores_gemma":[0.008559921,0.0008191757,0.001280097,0.001634074,0.0006220576,0.00349985,0.002634661,0.002282002,0.003103551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007777825,"about_ca_system_score_gemma":0.002041326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003814197,"about_ca_topic_score_gemma":0.008859846,"domain_scores_codex":[0.9978496,0.0009233137,0.0001365833,0.0006860804,0.0003020967,0.0001023314],"domain_scores_gemma":[0.9962554,0.002229661,0.0002932203,0.0004335483,0.0006665016,0.000121625],"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":[0.0004887262,0.0004032548,0.006087775,0.00145611,0.0003053943,0.0005334707,0.004464996,0.0463951,0.05599121,0.01325974,0.03221998,0.8383942],"study_design_scores_gemma":[0.0001339781,0.000190167,0.005579719,0.0001872816,0.0001534829,0.000254325,0.002086681,0.8751801,0.0339221,0.02949776,0.05269077,0.0001236626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03002363,0.0008858202,0.9361261,0.0005346992,0.0001432483,0.0003081493,0.004419298,0.02464534,0.002913731],"genre_scores_gemma":[0.2667346,0.0004096953,0.7092538,0.0001593062,0.0001551937,0.0006920813,0.01722921,0.001726996,0.003639101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003814197,"threshold_uncertainty_score":0.01167303,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04101422898557865,"score_gpt":0.3263863849262883,"score_spread":0.2853721559407096,"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."}}