{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002184488,0.000143523,0.0001332958,0.00009345633,0.0001199772,0.0008776579,0.0008574213,0.0000797447,0.0001345638],"category_scores_gemma":[0.00001000808,0.0001166347,0.00004885248,0.0002679315,0.00001715036,0.001470316,0.0003224855,0.0002092222,0.00001632926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007257186,"about_ca_system_score_gemma":0.0001728899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006341453,"about_ca_topic_score_gemma":0.0002267853,"domain_scores_codex":[0.9987539,0.0000585547,0.0001790023,0.0004895903,0.0002358453,0.0002831122],"domain_scores_gemma":[0.9992546,0.0000589768,0.00003657587,0.0005431183,0.00002776375,0.00007899267],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001255859,0.0001282844,0.0001457361,0.0001266526,0.00005304885,0.0002285486,0.006775391,0.5548966,0.05305463,0.2626763,0.001075053,0.1208271],"study_design_scores_gemma":[0.0001684136,0.0000108112,0.0000103698,0.00005391235,0.000008089606,0.00001570183,0.0001659253,0.9904932,0.003722947,0.004679222,0.0005062644,0.0001651723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08853353,0.0002177062,0.9081439,0.0004095335,0.0005788172,0.0002022456,0.00001370668,0.0002895139,0.001611041],"genre_scores_gemma":[0.8972467,7.128286e-7,0.1015224,0.0002939835,0.0001356648,0.000005422124,0.000009634271,0.00001505229,0.0007704555],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8087131,"threshold_uncertainty_score":0.8463275,"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."}}